Voice Biometrics Digest

Happy New Year!

2011-12-30T17:36:00.004-05:00

Wishing all a happy, healthy and prosperous 2012!

Let's see if IBM's biometrics predictions come to fruition.

Interesting Article about Biometrics

2011-10-29T14:19:00.001-04:00

Click here to read the article 'Is Biometrics The Answer To The Authentication Question?'

Opus Research to Convene Voice Biometrics Conference in Amsterdam

2011-02-05T16:10:00.004-05:00

On March 23-24, 2011, Opus Research will convene the sixth Voice Biometric Conference in Amsterdam NL. According to Opus Research, this year’s conference will "showcase the ever-expanding set of present solutions and future opportunities for voice biometrics to support authentication for mobile carriers and contact center operators at banks, insurance companies, government agencies and telecommunications firms, as well as identification opportunities and other forensic applications for law enforcement agencies around the world."

Click here for information about the conference.

Nuance Acquires PerSay

2011-01-17T15:51:00.006-05:00

PerSay, long recognized as one of the leaders in the voice biometrics space, was acquired by Nuance Communications, Inc. late last year. In an article on tmcnet.com, Chuck Buffum, Vice President of Authentication for Nuance is quoted as saying “PerSay’s voice biometrics products are currently in use across a range of applications, including remote transactions via contact centers and the Internet, password reset, offender monitoring, voice mining, and time and attendance. Together, the companies can accelerate the growth and adoption of the emerging voice biometrics market segment.”

I wish Almog, Ariel and the rest of the PerSay team the best of luck!

Another One Bites the Dust

2010-12-31T14:24:00.004-05:00

As we end 2010, another voice biometrics vendor has ridden off into the sunset. According to a press release, Ivrnet, Inc., a Canadian communications company, has acquired Diaphonic's voice biometrics software at "minimal cost." The press release goes on to say that Ivrnet plans to "fully integrate the voice biometric software into their entire line of speech products, with an aggressive marketing campaign set to begin in March 2011."

I'm afraid that this news does not bode well for the voice biometrics industry.

Citibank to Roll Out Voice Biometrics in Australia

2010-11-07T14:00:00.003-05:00

According to an October 15, 2010 article in zdnetasia.com, Citibank Australia is planning to roll out voice biometrics for identification to select early adopters.

Citibank Australia CEO Roy Gori stated "I think the next step in the evolution of security is voice biometrics. A person's voiceprint is more accurate than their fingerprint, iris or any other means of identification."

According to Gor, implementing voice biometrics would save Citibank Australia a lot of time and money, because it would cut out the traditional asking of questions for identification. He also stated that the next step after testing is completed is to get people to register and agree to it. Trials began six weeks in August, and early adopters could be using the system by the beginning of 2011.

Voice Biometrics Helps Uncover Terror Plot in Europe

2010-10-06T12:20:00.004-04:00

According to an October 5 item from the Associated Press,"the British eavesdropping agency GCHQ deployed voice identification software to help uncover the plot that officials say has targeted Germany, Britain and France." The article goes on to say that voice biometrics has played a role thwarting other terror plots in the past.

Voice biometrics experts believe that the technology has strong potential for streamlining intelligence operations. For example, both the U.S. and British intelligence gather huge amounts of electronic eavesdropping data. Persay's CEO, Almog Aley-Raz offered that "using voice biometrics could allow officials to scan a large number of phone conversations for several suspects' voices."

Voice biometrics may not be perfect (i.e., subject to background noise, etc.) but it has proven to be a valuable tool in the ongoing war on terror.

VoiceVault Offers Voice Biometrics Smartphone Developer Program

2010-09-14T12:51:00.001-04:00

A September 8 item on TMCnet.com announced that VoiceVault is now offering a voice biometric Smartphone Developer Program for VoiceVault Enterprise.

According to the article, the program includes several tools and resources that enable developers to design voice biometric-enabled smartphone applications. VoiceVault offers support to various smartphone platforms, including iPhone, Android and Blackberry.

Lee Cottle, Global Executive Vice President at VoiceVault, said that “smartphone users expect robust security and ease of use as a matter of course, and voice biometrics is a key technology to deliver this.” VoiceVault currently offers its VoiceVault Enterprise voice biometric enrollment, authentication, and signature components through 3G or WiFi networks, but has plans to provide an embedded on-device capability as well.

ANSI Standard for Voice Biometrics

2010-08-30T16:46:00.005-04:00

An item on SpeechTechMag.com indicates that "the American National Standards Institute has published INCITS 456: Speaker Recognition Format for Raw Data Interchange (SIVR-1), a standard governing the type and format of data that should be included with shared audio files used for speaker identification and verification." Judith Markowitz, president of J. Markowitz Consultants is the editor of the standard, which was 4 years in the making.

The types of data to be included with the file are: the bandwidth used to make the recording; date and time of the recording; type of channel that was used to record the data, such as a wireless or landline phone; information about the speaker, such as gender, age, language, and accent; the input device used; security used, such as the type of encryption; and the sampling rate. According to the article, the format is intended to be vendor-neutral.

It should be noted that, although the standard is not mandatory, it can be very useful to organizations such as military, intelligence and law enforcement that often share data about potential threats.

Competition for Authenticating Mobile Phones via Biometrics Heats Up

2010-08-25T11:47:00.004-04:00

An August 14 item on ThirdFactor.com announced that Animetrics has released new facial recognition authentication on certain mobile phones.

According to the article, “the service, called FaceR CredentialME, is available on devices using the Android, Windows Mobile and RIM operating systems on the Sprint 3G or 4G networks and was launched in conjunction with Troy Security Solutions, a mobile products and solutions provider.”

“The biometric service allows a user to authenticate their identity via unique characteristics in their face recorded from the phone’s embedded camera for anything such as basic online services or corporate specific services. Further, the biometric authentication can be used to entirely replace standard login methods or layered on top of them as a second factor of authentication.”

This announcement comes on the heels of PerSay’s introduction of a voice biometrics solution for iPhones and Bio-Key’s upcoming release of a fingerprint biometrics solution for mobile phones.

The race is on!

Voice Biometrics is in the Army Now!

2010-08-11T12:42:00.000-04:00

According to an item in “Government Computer News”, the United States Army is developing a major biometrics depository – including voice. The biometrics information is captured from all foreign nationals, including local nationals and third-country nationals, who are eligible to access bases in areas of conflict.

The article describes the process as follows: “It starts with the person’s employer filling out a paper application, knowing what privileges they should have and whether they should be escorted or not. That goes into an automated system along with the person’s biometric information and gets vetted against databases in West Virginia, which includes the FBI database. So then that information — hit [or] no hit — gets fed back to somebody at the local base, because every local commander gets to decide who can or can’t come on his base. And based on that information, whether it’s innocuous or whether they think it shows a threat, as well as other sources of information, they make a decision whether to allow that person on base. If they say “yes,” then the person is badged with a card that looks a lot like a Common Access Card.”

When the person arrives at the base, their card is first checked to ensure validity. Their biometrics (sample) are then compared against the biometrics (base) stored on the card to ensure that the person is who they claim to be.

PerSay Delivers Voice Biometrics Solution for iPhone, iPad and iPod Touch

2010-08-03T09:55:00.003-04:00

According to a press release, PerSay’s VocalPassword™ voice biometrics functionality is now available for iPhone™, iPad™ and iPod Touch™ applications. The voice biometrics functionality, which interfaces with a VocalPassword™ web service interface, uses a simple spoken pass phrase which enables single / multi-factor voice-based authentication. By combining it with the device ID, and / or a password, a triple-factor authentication is enabled.

Almog Aley-Raz, PerSay’s CEO, stated “iPhone and iPad users are demanding friendly Apps that utilize the most advanced technology for enhanced experience. By eliminating keyboard use, as well as the need for auto-filling names and passwords which poses a security risk, the PerSay solution provides optimal usability with maximum protection. Sensitive enterprise and personal applications, including mobile banking, social networks, payment services, membership clubs, and many more, can now provide their users with a sleek and innovative, yet strong authentication experience.”

As an iPhone user, I’m looking forward to demoing PerSay’s application.

Missed Opportunity for Voice Biometrics to Secure Smartphones!?

2010-07-28T11:18:00.003-04:00

Last week, there was an item on EnterpriseMobileToday titled “Smartphones to Get Biometric Identity Platform for Mobile Security". For a brief moment, I was excited about the prospect of voice biometrics playing a major role in this rapidly expanding market. Unfortunately, my hopes were dashed as soon as I started reading the article and learned that the biometric the title referred to was "fingerprint recognition".

Now I have nothing against fingers; I have ten of them myself. It’s just that voice biometrics seems like such a natural choice for a device that has a microphone and speaker. As a matter of fact, in March I blogged about the feasibility of securing smartphones with voice biometrics. This is a golden opportunity and I hope the voice biometrics industry is able to deliver a robust solution before it’s too late.

Old MacDonald Had a Farm…with Voice Biometrics

2010-07-20T13:14:00.001-04:00

A recent article on TMCnet.com described how some farmers in India are using voice biometrics to manage contract farming without being physically present.

According to the item, “farmers make a call to their organization's central "Voice ERP" system and feed in information they want to share with tillers. The information gets stored in the database and gets converted into text. The system then generates an SMS, which is sent to the mobile phones of the tillers.” The article goes on to say that “farmers are provided unique identity codes to ensure only authorized people access an organization's Voice ERP database. For additional security, a voice biometrics check can also be performed.”

The "Voice ERP" system is provided by Uniphore Software Systems.

PerSay Wins 2010 Speech Industry Award

2010-07-14T10:52:00.005-04:00

Congratulations to Persay for winning the 2010 Speech Industry Award for Speech Security. Other recipients in the category included: Leaders: Agnitio and Raytheon/BBN; Vendor Contender: Loquendo.

The Speech Industry Awards are handed out each year by Speech Technology magazine. According to the magazine's website, "recipients were determined through an extensive process and proprietary rating formula that involves collecting industry analyst and consultant reviews, financial and corporate information, product and functionality assessments, and scores based on their importance to current and potential customers."

PerSay Ltd., with offices in Tel-Aviv, Israel and New York, is a provider of voice biometrics products.

Tongueprints to verify identity?

2010-07-06T11:19:00.004-04:00

An item in “Security World News” describes research being conducted at Hong Kong Polytechnic University’s Biometrics Research Center on the use of tongue scanning to identify individuals. “The tongue shapes of different people are different, and thus the tongue can be used to tell different subjects (apart),” says Lei Zhang, assistant professor at the university.

Here’s the abstract of Professor Lei Zhang’s research paper:

“Biometrics, which use human physiological or behavioral features for personal identification, currently face the challenge of designing a secure biometric system that will accept only the legitimate presentation of the biometric identifiers without being fooled by the doctored or spoofed measurements that are input into the system. More biometric traits are required for improving the performance of authentication systems. In this paper, we present a new number for the biometrics family, i.e. tongueprint, which uses particularly interesting properties of the human tongue to base a technology for noninvasive biometric assessment. The tongue is a unique organ which can be stuck out of the mouth for inspection, whose appearance is amenable to examination with the aid of a machine vision system. Yet it is otherwise well protected in the mouth and difficult to be forged. Furthermore, the involuntary squirm of the tongue is not only a convincing proof that the subject is alive, but also a feature for recognition. That is to say, the tongue can present both static features and dynamic features for authentication. However, little work has hitherto been done on the tongue as a biometric identifier. In this work, we make use of a database of tongue images obtained over a long period to examine the performance of the tongueprint as a biometric identifier. Our research shows that tongueprint is a promising candidate for biometric identification and worthy of further research.”

What's next?

Warning! Crude “Voice Verification Process” used to Scam Businesses

2010-06-23T09:45:00.001-04:00

An item out of Bakersfield, California (KERO 23) warns businesses of a new scam that uses a crude “electronic Voice Verification process.” Here’s how it works:

Let’s say you decide not to renew an existing contract (e.g., yellow pages advertising). The company calls you and asks you to confirm certain information, such as name, phone, etc., by providing “yes” and “no” answers to the questions. The company then claims that you answered “yes” to the terms of the renewal -- and will even play back a recording of you answering “yes” to the “renewal question.”

I can see this “process” being used to scam individuals as well. If you are a victim of this scam, immediately send a cancellation letter to the company. You may also want to contact the Better Business Bureau and Federal Trade Commission.

Voice Commerce Introduces Cloud-Based Voice Biometrics e-Commerce Platform

2010-06-16T11:06:00.002-04:00

A June 15, 2010 item on infosecurity.com discusses the introduction of Voice Commerce’s cloud-based voice biometrics e-commerce platform.

According to the article, there are two components to the platform – retailer and consumer. The retailer system, known as On4, “allows retailers to instantly set up and run their online business (e.g., stock control, shipping management, etc.), processing transactions using voice biometrics to authenticate/authorize their online and mobile-based electronic payments.” On4 is linked in to the Voice Commerce Payment system.

The consumer system, known as VoicePay, “allows consumers to set up their own voice biometric (base voiceprint) as an authenticator for use over the phone or mobile phone. The idea is that, once a user has set up their authenticator, any VoicePay-enabled retailer can use the biometrics and authenticate the user by simply calling him or her (and comparing the sample voiceprint to the base voiceprint).”

You may recall that I wrote about a similar mobile shopping application back in March. Let the games begin!

Consumers Prefer Voice Above Other Biometrics

2010-06-10T10:36:00.003-04:00

According to a Unisys study, cited in an article on the sourcesecurity.com Website, “the biometric measures ranked by consumer preference are: voice recognition (32%), fingerprints (27%), facial scan (20%), hand geometry (12%), and iris scan (10%). This ranking seems to confirm that people prefer convenience and familiarity when choosing a biometric technology. “

Voice biometrics compared to other biometrics is:

1) User-friendly - speaking is natural and requires no special effort
2) Cost effective - verification is accomplished via telephone or microphone
3) Convenient - enables remote verification of a person’s identity

Implanted Microchips to Verify Identity?

2010-06-07T12:23:00.002-04:00

An article in the June 5, 2010 Sydney Morning Herald (Australia) describes how one man is using an implanted radio frequency identification (RFID) microchip to verify his identity when he logs on to his computer, unlocks his car, etc. Washington State resident Amal Graafstra is one of approximately 300 people worldwide who have had an RFID chip implanted in their body. In Mr. Graafstra’s case, the chip, the size of a grain of rice, was implanted in his hand by a cosmetic surgeon in a five minute procedure.

Once the chip is implanted, various devices (e.g., locks, etc.) can be programmed to recognize the device. In spite of undergoing the implant, it’s interesting to note that Mr. Graafstra believes biometrics – including voice -- will prove superior for verifying identity. His stated goal is simply to create a dialogue on technology and its uses.

The article points out some additional potential benefits of the technology, such as the ability to “identify an Alzheimer's patient who has become lost or warn that an unconscious patient is allergic to penicillin.” However, there are obviously a myriad of social and privacy concerns as well. We’ll have to keep an eye on this one.

SpeechTEK to Feature a Dedicated Voice Biometrics Track

2010-06-01T14:54:00.003-04:00

SpeechTEK, an annual voice solutions conference, will be held August 2-4, 2010 at the New York City Marriott Marquis Hotel. This year’s conference will feature a dedicated voice biometrics track with three sessions:

• Understanding Voice Biometrics
• Voice Biometrics to the Aid of Preventing Identity Theft
• Determine the Identity of the Caller

In addition, several voice biometrics vendors, including Convergys and Persay, will be exhibiting. Additional details about the conference can be found on SpeechTEK’s Website.

There is free admission to the exhibit area. I hope to see you there.

Voice Biometrics Goes Back to Jail

2010-05-25T10:50:00.003-04:00

In an earlier posting, I described the use of voice biometrics in jails/prisons to prevent illegal activity by inmates. An article in today’s Mt. Vernon Register-News reinforces the need for voice biometrics to prevent inmates from perpetrating phone scams.

According to the item, inmates at the Jefferson County Detention Center (Illinois) are using pay phones to call unsuspecting citizens and scam them. “This time, they are using a little different technique,” Jefferson County Sheriff Mulch explained. “The caller uses a calling card that has the ability to program it to Spanish. The person receiving the call only understands the ‘Jefferson County Detention Center,’ portion, and they hit the prompt to speak with the person. They get the detainee, who then speaks in English.”

The detainee pretends to be a police officer who is trying to identify someone who has been involved in a traffic accident, and the phone number they called was on the victim’s cell phone.

“People want to help and ask what they need,” Mulch said. “They are told to dial star 72 and enter a series of eight numbers, or they tell them to dial 1172 and a series of numbers. What that does is locks the phone number in and they can then use a calling card to make calls across the country using the victim’s phone number.”

Sheriff Mulch is in the process of researching the use of voice biometrics to track inmates’ fraudulent calls.

American Safety Council uses Voice Biometrics to Validate Identity of eLearning Students

2010-05-24T13:15:00.003-04:00

The American Safety Council, an Orlando Florida based provider of eLearning courses, uses voice biometrics to validate student identity for defensive driving programs in New York and New Jersey. At various intervals during the course, students are required to validate their identity, via voice biometrics, within 60 seconds.

Two months ago, I posted an item about a similar voice biometrics application being offered by I DRIVE SAFELY. Does anyone know if they one and the same?

Alternative to Voice Biometrics? Online "Handwriting and Gesture" Biometrics

2010-05-20T14:48:00.003-04:00

ThirdFactor.com recently wrote about a technology company located in Dallas, Texas, Biometric Signature ID, which developed an online handwriting and gesture biometrics application -- BioSig-ID™. According to the Company’s Website, BioSig-ID is an ideal solution for verifying the identity of people using online applications (e.g., distance learning, online banking, etc.). The BioSig-ID enrollment and verification processes work as follows:

Enrollment Process
• An individual is asked to draw their unique signature with any characters/shapes/initials, using their mouse, in an online box. This process is repeated three times to create a “base” signature
• The individual is then directed to a second non-biometric layer of security called Click-ID Technology (i.e., they click on a selection of objects) to complete the enrollment process. There is even a third-level of security using complex security questions

Verification Process
• An individual accesses the online application and is asked to draw their signature once. This process creates a “sample” signature
• If the individual’s “sample” signature matches their “base” signature, access is granted to the application
• If the signatures don’t match, additional levels of security are activated

BioSig-ID was recently selected to complete a pilot trial at University of Maryland University College.

Voice Biometrics Facilitates Automated Password Resets

2010-05-14T15:47:00.004-04:00

At last week’s Voice Biometrics Conference, Mike Matthews, UK Service Desk Product Manager at Atos Origin (IT services company), presented a compelling case study on the use of voice biometrics to automate password resets.

Mike started off by listing some examples of password reset “pain” compiled from Atos Origin clients:
• Up to 25% of all contacts to the help desk
• Up to 15 minutes to reset a password
• Up to $22.50 per contact
• Post weekend and holiday spike in contacts
• Support unavailable outside of normal office hours

He then proceeded to describe a fully-automated approach to password resets, using voice biometrics to verify the user’s identity, and identified the benefits. Using an automated approach…

• Resetting a password takes, on average, 1 minute
• The need for human intervention to complete low level tasks is reduced, significantly lowering overhead
• Password resets are not affected by heavy call volumes and, therefore, spikes in contacts become a thing of the past
• Password reset is available 24/7 365 from anywhere in the world, using any type of phone

Mike concluded with the following ROI example:

Company performs approximately 115,000 password resets per year:
• Currently costs $12 per call, or $1,380,000 per year
• Lost productivity, using an average of 7 minutes per call, amounts to 13,500 hours

Using an automated password reset (with voice biometrics) approach, the cost per contact is reduced to $7.50 per call, or $862,500 per year:
• $517,500 savings per year
• Help desk downtime reduced to approximately 2000 hours (i.e., reduction of 11,500 hours per year)

Voice Biometrics Case Study - T-Mobile Netherlands

2010-05-12T15:58:00.005-04:00

At last week’s Voice Biometrics Conference, Daniel Hendling, International Program Manager, Sales & Customer Service at Deutsche Telekom, gave a lively presentation of T-Mobile Netherlands’ plans for its upcoming voice biometrics pilot. According to Daniel, complex methods of customer authentication, currently in place, can harm both customers and businesses. For example, customers may get annoyed having to remember different passwords and businesses may see an increase in call handling time – which can lead to customer satisfaction and loyalty issues.

T-Mobile Netherlands selected Agnito’s KIVOX voice biometrics product to achieve the following objectives:
1) Reduce the average handling time spent on caller verification
2) Provide an enhanced user experience
3) Enable reliable self service options in the short to mid-term

Enrollment
• The customer will be prompted to provide their PIN code and repeat three sentences, three times (i.e., “base” voiceprint will be captured and stored in the database)

Verification
• The customer will be prompted to repeat one sentence once (i.e., “sample” voiceprint is captured)
• If the “sample” voiceprint matches the “base” voiceprint, the customer’s identity is verified

T-Mobile Netherlands expects to realize the following benefits from their voice biometrics application:
• Improved customer satisfaction
• Decreased call handling time
• Increased level of security
• T-Mobile Netherlands will be perceived as an innovation leader

The pilot is scheduled to commence July 2010. Stay tuned!

Voice Biometrics to Monitor Florida Home Health Providers

2010-05-10T11:24:00.002-04:00

Sandata, LLC, a provider of IT solutions to the home health care industry, has announced the upcoming deployment of a voice biometrics system that will enable the Florida Medicaid program to verify that home health services were actually delivered to the recipient. The pilot, scheduled to begin July 1, 2010, will target home health providers in Miami-Dade County that participate in the Florida Medicaid program. According to Harold S. Blue, Sandata’s CEO, the voice biometrics system will help ensure that the "The Florida Agency for Health Care Administration (which administers Medicaid) only pays for the '5 rights' - the right service provided, at the right location, at the right time, for the right patient, by the right caregiver."

The voice biometrics system, which is powered by PerSay’s VocalPassword™ product, will confirm home health visits by taking calls from home health personnel (nurses and home health aides), who directly provide services to Medicaid recipients, at the beginning and end of each home health visit using the recipient's home telephone. The system will verify that the correct caregiver provided the service by comparing their sample voiceprint to their base voiceprint on file.

Voice Biometrics Conference 2010

2010-05-06T15:47:00.002-04:00

I just returned from the annual Voice Biometrics Conference – where the key players of the voice biometrics industry gathered to compare notes, present case studies and discuss future plans. Kudos to the Opus Research team -- Dan Miller, Derek Top and Pete Headrick -- for orchestrating an excellent event.

Over the next week, or so, I plan to share some new case studies that should resolve any lingering concerns about the efficacy of voice biometrics technology. The bottom line is that voice biometrics systems have been deployed at leading organizations throughout the world, and are successfully identifying and verifying individuals by their voice 24/7.

My take away from the conference is as follows: the voice biometrics industry offers an excellent solution, with a compelling value proposition, but still appears to be treading water in the market place.

New iPhone biometrics application? Not sure…

2010-05-03T09:37:00.006-04:00

An article on “The New Zealand Herald” Website, states that a New Zealand technology company, FeelGudApps, has developed a new biometrics application for the iPhone. The developers claim that the app, named ‘Feelie’, can broadcast how you're feeling to registered recipients. The item goes on to describe how Feelie works.

Feelie monitors a person’s behavior (e.g., terseness of texts and emails, amount of movement, etc.) for two to three days. A base profile is then constructed based on data from psychological studies. From then on, the person's emotional state is dynamically updated and broadcast to their registered recipients. A color-coded tinge over the person’s profile picture identifies how they're feeling as follows:

• Yellow – happy
• Blue - calm
• Green – nervous
• Purple - lying
• Red – angry

I was hoping to put Feelie through its paces -- to see if there was a voice biometrics angle to be exploited. Unfortunately, I could not find any reference to the app in the iTunes store. Too good to be true?

Online Banking and Voice Biometrics – Odds and Ends

2010-04-30T08:25:00.003-04:00

Online fraud complaints jumped 23 percent in 2009 to 336,655 with a total loss of $560 million, more than doubling the $265 million in losses from 2008, according to an article in the May 2010 edition of Bank Technology News. Additionally, a recent Gartner survey found “nearly half of people who don't use online banking listed security as a reason.” The item goes on to say that financial institutions will probably seek out-of-band security solutions (e.g., voice biometrics) as an additional factor of authentication.

This should be music to the ears for voice biometrics vendors. After all, voice biometrics is an ideal way to remotely authenticate online banking customers – and the technology is beginning to get some legs. For example, a recent posting in my blog mentioned that the top three banks in Israel have all implemented public-facing voice biometrics solutions.

One cautionary note comes from George Tubin, senior research director, TowerGroup, who says “voice biometrics still needs work. There's background noise and connection issues. There's also the matter of how well it functions." I’ve been hearing these concerns since I entered the space five years ago – and they continue to be a serious hurdle. It is incumbent upon the voice biometrics industry to find a way to overcome these legitimate concerns. The potential remote authentication market is just too big!

Voice Biometrics is the Right Choice for Contact Centers

2010-04-28T10:29:00.014-04:00

Voice biometrics is a proven technology which can reduce contact center operating costs, increase security, enhance customer service and facilitate regulatory requirements (see my article on SpeechTechMag.com).

Voice biometrics has been successfully deployed at contact centers throughout the world. Want to learn more? Here are links to five case studies:

Australia Health Management
Bell Canada
National Australia Bank
TD Waterhouse Canada
Vodafone Turkey

Embedded Voice Biometrics Solutions

2010-04-26T12:16:00.002-04:00

An article in The Economic Times (India)states that voice biometrics is not yet a viable option for logging on mobile devices such as computers and smart phones. The author claims that these devices are not sophisticated enough to handle biometric technology. I don’t know if that’s the case.

What I do know is that embedded voice biometrics, where enrollment and verification functionality is self-contained, is a natural fit for smart phones and other devices with a microphone. Additionally, several voice biometrics vendors (e.g., PerSay) are actively engaged in developing embedded solutions.

One company, Sensory, Inc., based in Sunnyvale, CA, has been providing embedded voice biometrics solutions to the toy and robotics industry for years. I’ve seen this technology in use in a toy voice activated biometric-safe. According to Sensory’s Website, their product’s “equal error rate (where the probability of an incorrect acceptance equals that of an incorrect rejection) ranges between 0.01-7% depending on the number of words and whether the passwords are known to the fraudster.”

I’m certain that, in the not too distant future, we’ll have a robust voice biometrics solution which can be embedded in a variety of mobile devices.

Voice Biometrics and HIPAA

2010-04-23T13:13:00.003-04:00

Jason Gaya posted an item about HIPAA and biometrics on his emPower LMS blog that, in my opinion, makes a strong case for a voice biometrics solution. HIPAA mandates strict protection of health records. One way to ensure compliance is to implement tighter identity verification through multi-factor authentication. The three factor categories are “something the caller knows” (e.g., account number), “something the caller has” (e.g., hardware token) and “something the caller is” (e.g., voiceprint).

In his article, Gaya identifies several features that a biometric system used to secure health records should have:

• Cost-effective
• User-friendly
• Easy to deploy
• Fast verification process
• High degree of accuracy (e.g., low crossover error rate (CER))
• Interoperability
• Customized to the environment (e.g., factor in background noise of emergency room, etc.)

I believe that a voice biometrics solution has those features. Additionally, it’s a proven technology which can ensure HIPAA compliance by allowing only authorized access to health records.

Criteria for Selecting a Voice Biometrics System

2010-04-21T11:19:00.004-04:00

An item on policeone.com, by Thomas Bush III, Strategic Advisor for BIO-key International, caught my attention. In the article, “How to buy police biometrics products,” he presents guidelines, or, what he calls the “Four E’s,” for selecting biometrics systems. Although Mr. Bush focuses on fingerprint biometrics, I believe his criteria are spot-on for voice biometrics as well. Here they are:

• Effectiveness: “The basic measure of any authentication solution is accuracy. However, biometrics accuracy often comes with a price - in the form of “false negatives” or improper rejection of individuals who should have been successfully authenticated. While this is often attributed to “user error,” the potential end result in user frustration and time lost in re-authenticating must still be part of the measurement of overall effectiveness.”

• Ease of deployment and use: “No technology can be effective unless, and until, it’s operational and in regular use. A “bleeding edge” biometrics solution, even if it’s potentially more effective, may never get out of pilot, and one that users find confusing or cumbersome may not even make it that far. The solution should be easy to deploy and maintain and shouldn’t require significant changes to business processes.”

• Enterprise-wide capability: “While an organization may deploy an authentication solution to meet a single need today, it makes sense early in the selection process to look at where and how the use of biometrics may be expanded to meet future needs. This can save money and simplify administration.”

• Economic considerations: “Keeping costs under control is important – even when budgets aren’t under the strain they are today. …While the software is usually proprietary, a strong ongoing maintenance and support agreement can help ensure that the software can be enhanced on an ongoing basis, extending the life cycle of the solution, even as technology changes.”

Voice Biometrics Opportunity -- Authenticating the Identity of e-Prescribers

2010-04-19T12:06:00.005-04:00

The March 31, 2010 Federal Register included an interim final rule posting by the Drug Enforcement Agency (DEA) that would permit hospitals, healthcare providers, and pharmacies to use electronic prescriptions in the dispensing of controlled drugs. Although providers may currently create electronic prescriptions for controlled substances, those prescriptions cannot be transmitted as electronic data files to the pharmacy. Instead, the e-prescriptions must be printed out for signatures or faxed to a pharmacy. The DEA's rule would eliminate the need for a manual process.

Of particular interest to the voice biometrics community is that the new rule allows "biometrics" (including voice) to be used, as one of two-factors, to authenticate the identity of the e-prescriber. Specifically, the rule states that the “DEA is allowing the use of a biometric as a substitute for a hard token or password.” For a biometric to be acceptable, it must meet several requirements (e.g., a “false accept rate” of 0.001 or better, etc.).

The opportunity is there. Who will be the first to step up to the plate?

Top Three Banks in Israel Deploy Voice Biometrics

2010-04-15T07:44:00.005-04:00

According to a press release, PerSay has completed the deployment of public-facing voice biometrics systems at the top three banks in Israel – Bank HaPoalim, Bank Leumi and Discount Bank. Applications range from automatic PIN reset to multi-factor identity verification.

Bank HaPoalim’s Contact Center manager commented about voice biometrics on Israeli TV as follows:”Besides the efficiency we gained by eliminating authentication questions, we have significantly improved our service accessibility and customer experience.” Also, Israel’s former Chief Scientist (and PerSay Board Member), Dr. Orna Berry, commented that she expects to see a global expansion of voice biometrics in the next few years to accessing remote services and applications over the phone, Internet, as well as mobile devices.

This latest news can only enhance the credibility of voice biometrics as the right technology for remote identity verification in contact centers. As my recent article on speechtechmag.com asks, “What’s Everyone Waiting for?”

Opus Research: Voice Biometrics Webcast Recap

2010-04-14T09:22:00.005-04:00

Dan Miller and Derek Top, Opus Research, along with Paul Heirendt, CEO of TradeHarbor, presented a Webcast yesterday titled “Meeting New Demands for User Authentication.”

The central theme was that voice biometrics should be seen as an enabling technology (i.e., for transactions and interactions) over a number of channels and networks. Paul presented several examples, including:

• Identity and authentication – voice biometrics authenticates that the person is actually who they claim to be

• Increased customer convenience and reduced operations costs – live agent knowledge-based authentication takes 30 seconds to 2 minutes while voice biometrics authentication takes less than 9 seconds

• Privacy protection – voice biometrics strengthens authentication which can lead to a stronger privacy protection policy

Click here to view the archived Webcast.

Alternative to Voice Biometrics? Eye-Movement Patterns

2010-04-12T11:06:00.003-04:00

While scanning a press release about Innovate!2010, I read about an innovative biometrics company based in Israel. ID-U claims to have developed the first stimuli-driven biometric system, based on the uniqueness of a person's eye-movement patterns.

According to ID-U’s Website, the system works as follows: “the person to be identified (user) watches a moving target (visual stimulus) on a monitor, while a small, low-resolution camera acquires the user's eye-movement response; a processing unit, either inside the local device or remotely located at another physical site, uses both the stimuli and response to identify the user.” The “sample” pattern is compared to a “base” pattern previously captured. I’m not 100% certain if the person can enroll via their own camera (e.g., computer, cell phone, etc.).

ID-U lists several advantages of using eye-movement patterns, including: the product is software driven, it’s virtually impossible to reproduce a user’s response to stimuli and the product’s inherent liveness detection. Of particular interest to the voice biometrics industry is the Company’s statement that their biometrics technology can be used to secure mobile transactions by simply using a cell phone’s display and camera.

I plan to learn more about this technology (e.g., enrollment process, failure rates, etc.) and report back.

Voice Biometrics Case Study: Australian Health Management

2010-04-09T12:13:00.003-04:00

In 2007, Australian Health Management (AHM), one of Australia’s top 10 health services providers with 250,000 members, introduced a voice biometrics system to validate member’s identities. Salmat (formerly VeCommerce) implemented the voice verification system, which is powered by Nuance Verifier™. According to AHM’s Website, the voice verification system was deployed to enhance member service. For example:

• Members would no longer need to go through the manual verification process every time they call
• Membership details would be accessed quicker to reduce waiting time
• Member’s health insurance information would be more secure

Enrollment Process:
• The enrollment process is voluntary and guided by a live agent
• Member is prompted to say their membership ID number
• This process creates the client’s “base” voiceprint and stores it in the database for future use

Verification Process:
• Member calls AHM and is prompted to say their membership ID number
• This process creates the member’s “sample” voiceprint which is then compared to their “base” voiceprint in the database
• If the voiceprints match, the member’s identity is verified
• If the voiceprints don’t match, the member is transferred to a live agent

Using voice biometrics, AHM is saving an average of 30 seconds per call.

PerSay Forms Alliance with Global Telecom Solutions Provider

2010-04-07T09:23:00.006-04:00

According to a press release, PerSay has entered into an alliance with Huawei, a global telecom solutions provider with headquarters in the People's Republic of China. The agreement enables Huawei to offer a pre-integrated voice biometrics enabled IP Contact Center solution across enterprises globally.

Reacting to the announcement, Almog Aley-Raz, PerSay’s CEO stated “While more and more solution providers, system integrators, and value added resellers realize the benefits of voice biometrics, Huawei has taken a unique proactive approach, integrating voice biometrics into its product suite and offering it to its customers. With this strategic alliance, we are more confident than ever that voice biometrics and PerSay products will play a role in every modern contact center.”

Coming on the heels of the recent TradeHarbor-USAN partnership announcement, I'm hopeful that contact centers will soon begin deploying voice biometrics en masse!

9EZG58FGVCXG

Voice Biometrics Basics - Standards

2010-04-05T15:23:00.005-04:00

The majority of voice biometrics platforms and applications are proprietary in nature. This eliminates any opportunities for interoperability among the various components (i.e., enrollment, verification, database, etc.) that comprise a voice biometrics system. For example, a ‘sample’ voiceprint captured via system ‘B’ cannot be compared to a ‘base’ voiceprint captured by system ‘A’, and so on.

There are several organizations actively engaged in the development of biometric (including voice) industry standards, including:
• American National Standards Institute (ANSI)
• BioAPI Consortium (BioAPI)
• International Standards Organization (ISO)
• Internet Engineering Task Force (IETF)
• World Wide Web Consortium (W3C)

Two examples of standards under development include:

Media Resource Control Protocol (MRCP): MRCP is a protocol, developed by Cisco Systems, Inc., Nuance Communications, Inc., and SpeechWorks, and backed by the IETF, that allows interoperability among various speech resources within telephony applications.

Voice Extensible Markup Language (VoiceXML): According to Wikipedia, “VoiceXML is the W3C’s standard XML format for specifying interactive voice dialogues between a human and a computer. It allows voice applications to be developed and deployed in an analogous way to HTML for visual applications. Just as HTML documents are interpreted by a visual web browser, VoiceXML documents are interpreted by a voice browser or IVR.”

Identity Thieves/Fraudsters Find New Hunting Grounds

2010-04-02T10:27:00.003-04:00

Identity thieves and fraudsters continue to find new ways to ply their trade. An article in today’s "Voice&Data" Magazine identifies three non-traditional domains where identity related crimes are proliferating:

E-Payments
New online and mobile payment methods, such as peer-to-peer (P2P) payments (already available as a Facebook application) are creating opportunities for identity thieves. According to the article, some of these payment modes do not ensure adequate identity verification when processing a transaction.

Mobile Payment
Many mobile devices can now be used as “electronic wallets” to facilitate financial transactions. Unfortunately, this technology provides additional opportunities for fraudsters to not only steal your identity, but your money as well.

Social Media
Social networking sites, such as Facebook and LinkedIn, contain personal information which can be “borrowed” by identity fraudsters to create fake accounts in your name.

The article goes on to recommend the use of multi-factor authentication, with biometrics, including voice, as one of the factors, to help prevent identity fraud.

For more information on identity theft, including steps you can take to safeguard your personal information, click here.

Voice Biometrics Case Study - National Australia Bank

2010-03-31T10:37:00.005-04:00

In 2009, Telstra , an Australian telecommunications company, deployed a voice biometrics identity verification system at the National Australia Bank. The system, dubbed “Speech Security,” uses Salmat VeCommerce‘s VeSecure® Biometric solution (which is powered by Nuance Verifier™). According to NAB’s Website, Speech Security was introduced to “improve the customer experience on NAB’s telephone banking and enhance security and privacy by removing the need for customers to remember PINs and passwords.”

Enrollment Process:
• The enrollment process is voluntary and takes approximately three minutes
• Customer is prompted to repeat a series of words
• This process creates the client’s “base” voiceprint and stores it in the database for future use

Verification Process:
• Customer calls NAB and is prompted to say their account number and date of birth
• This process creates the customer’s “sample” voiceprint which is then compared to their “base” voiceprint in the database
• If the voiceprints match, the customer’s identity is verified

Speech Security was initially rolled-out to 3.3 million NAB customers.

Voice Biometrics Case Study – I DRIVE SAFELY

2010-03-26T12:10:00.006-04:00

During yesterday’s Speech Technology webinar, William Morrow, Chairman and CEO of CSIdentity Corporation, presented a case study on the use voice biometrics in the distance learning space. In 2008, I DRIVE SAFELY, a provider of online defensive driving and traffic school courses, deployed the VoiceVerified® voice biometrics solution to enforce the academic integrity of students.

A 2009 Speech Technology article, by Judith Markowitz, described the enrollment and verification processes as follows:

Enrollment
• During the online registration process, the student provides their phone number
• An automated outbound call is made to the student and they are prompted to repeat six separate five-digit phrases (i.e., “base” voiceprint is captured and stored in the database)

Verification
• At key course intervals (e.g., completion of chapter, etc.), an automated outbound call is made to the student and they are prompted to verify their identity by repeating a five-digit phrase (i.e., “sample” voiceprint is captured)
• If the “sample” voiceprint matches the “base” voiceprint, the student’s identity is verified and they are permitted to advance to the next phase of the course

Since 2008, I DRIVE SAFELY has enrolled over 60,000 voice prints and completed over 300,000 verifications.

Speech Technology Voice Biometrics Webinar - Summary

2010-03-25T16:11:00.005-04:00

This afternoon, Speech Technology hosted a voice biometrics webinar titled “How Verifying Your Customer’s Identity Can Save You Money.” The panelists were: Judith Markowitz (Consultant), Chuck Buffum (Nuance), William Morrow (CSIdentity) and Paul Heirendt (Trade Harbor). The moderator was David Myron (Speech Technology).

Judith Markowitz began the session with a review of voice biometrics basics. According to her, organizations deploy voice biometrics to:

• Combat identity theft and other fraud
• Protect personal data - privacy
• Comply with regulations
• Enhance convenience and simplify the authentication process

Judith also mentioned that voice biometrics has been deployed in the following sectors: financial services, healthcare, distance learning, telecom, transportation and government.

Chuck Buffum next presented an interesting overview of voice biometrics metrics. He discussed business, solution and technology metrics. Business metrics measure reduced operating expenses, improved customer experience/satisfaction and improved security. Solution metrics include: automated authentication rate, security rate (1 – imposter rate), offer acceptance rate, enrollment success rate, and re-use rate (opposite of opt-out after enrollment). Technology metrics include: false reject, false accept and enrollment success rate.

Chuck also discussed some of the factors that influence voice biometrics performance, including: richness of voice enrollment (i.e., broad and deep phonetic coverage), quality of audio sample (e.g., signal noise ratio) and environmental characteristics (e.g., background noise).

William Morrow stressed the growing rate of identity theft and fraud as a driver for deploying voice biometrics. From 2007 to 2009, there was a 37% increase in the number of victims. He said that the cost of identity fraud in 2009, in the U.S., was $54 billion. William ended by presenting a brief case study about the use of voice biometrics to ensure academic integrity for distance learning company “I DRIVE SAFELY” (IDS).

The final panelist, Paul Heirendt presented an overview of TradeHarbor’s voice biometrics product (VoiceSignatureService(SM)). He also addressed many of the benefits that organizations can realize by deploying voice biometrics.

When the presentations were over, the panelists addressed questions submitted by the participants.

The archived webinar should be available for viewing on Speech Technology’s Website.

TradeHarbor Partners with Call Center Solutions Provider

2010-03-23T10:53:00.004-04:00

According to a press release, TradeHarbor, Inc. has entered into a partnership agreement with USAN, a provider of hosted call center solutions, to offer its SaaS voice biometrics solution (Voice Signature Service(SM)) to USAN’s IVR services customers.

Bob Nelson, Vice President of Partner Development at TradeHarbor said that the Voice Signature Service(SM) will be deployed to authenticate inbound calls, as well as “online authentication for transactions made from computers and mobile devices based on outbound calls to their wired or mobile phones.”

I am pleased that USAN recognized the value of deploying voice biometrics to secure call center transactions.

Biometrics and Privacy Concerns

2010-03-22T15:29:00.005-04:00

The International Biometrics Group BioPrivacy Initiative™ has published an excellent list of privacy concerns as they relate to biometrics:

Personal Privacy. For some people, the use of biometrics is seen as inherently offensive. Being required to verify one’s identity through a finger-scan or voice-scan can be seen as intrusive, impersonal, or mistrustful. These objections to biometrics are based on personal privacy.

[My two-cents: I’m surprised that IBG considers finger-scans and voice-scans to be equally “intrusive.” Voice-scans can be captured via a telephone or microphone in a natural way – speaking.]

Informational Privacy. A more common objection to biometrics is based on informational privacy; how biometric data might be misused, tracked, linked, and otherwise abused. Potential privacy-invasive misuses of biometrics are as follows:

Unnecessary or unauthorized collection – gathering biometric information without the user’s permission or knowledge, or gathering biometric data without explicitly defined purposes

Unauthorized use – using biometric information for purposes other than those for which it was originally acquired

Unauthorized disclosure – sharing or transmitting biometric information without the user’s explicit permission

Unique identifier – using biometric information to track a user across various databases, to link different identities, and to amalgamate personal data for the purposes of surveillance or social control

Improper storage – storing biometric information in logical proximity to personal data such as name, address, social security number

Improper transmission – transmitting biometric information in logical proximity to personal data such as name, address, social security number

Forensic usage – using biometric information to facilitate investigative searches, which may be categorized as unreasonable search and seizure

Function creep – gradually using biometric data for a variety of purposes beyond its original intention and scope

[My two-cents: With the exception of military and law enforcement applications, I believe it is absolutely critical to provide full-disclosure (e.g., how data will be used, stored, etc.) to people who use a biometrics system.]

Voice Biometrics Case Study – Union Pacific Railroad

2010-03-19T12:59:00.007-04:00

In 2001, the Union Pacific Railroad deployed a customer-facing voice biometrics system to automate the release of empty railcars. The system was powered by SpeechWorks’ SpeechSecure product. [Note: SpeechWorks was acquired by Nuance in 2003.]

A 2004 whitepaper issued by the SANS Institute, provided the following description of the railroad's application:

“Union Pacific moves railcars back and forth across the United States every day. The railcars travel loaded in one direction and empty on the way back. When the loaded railcar arrives, the customer is notified to come pick up the contents. Once emptied, the customer needs to alert Union Pacific to put the railcar back to work. Union Pacific now has an automated system that utilizes voice authentication to allow a customer to release empty railcars. Customers enroll in the voice authentication system over the phone. When they call back to release an empty railcar, the system authenticates them and allows them to release their railcars. In this case, voice authentication has allowed customers to get off the phone faster, and Union Pacific to guarantee that a customer is not releasing a railcar that doesn’t belong to him.”

When a customer called the railroad's IVR, they were given the option to enroll in the system (i.e., provide a “base” voiceprint). Once enrolled, a customer could verify their identity by providing a “sample” voiceprint. If the voiceprints matched, the customer’s empty railcar was released. If the voiceprints did not match, the customer was transferred to a live agent.

Does anyone know if this application is still in use by the Union Pacific Railroad?

Securing Mobile Devices with Voice Biometrics – A Natural Fit

2010-03-18T18:06:00.005-04:00

Mobile devices, such as smart phones, often contain personal and confidential data -- and are very vulnerable to theft and loss. To prevent unauthorized use, most devices rely solely on single-factor password security. Unfortunately, passwords offer relatively weak protection as they can be forgotten, observed, stolen or hacked.

Voice biometrics, on the other hand, can provide robust security and is also a natural fit for smart phones and other mobile devices with a microphone. Let’s see how the technology would work with mobile devices. There are two approaches:

• Embedded – all voice biometrics functionality (enrollment and verification) is self-contained on the mobile device
• Remote – some voice biometrics functionality (e.g., “voiceprint capture”) resides on the mobile device and the remaining functionality lives on a server

Several organizations are actively engaged in developing voice biometrics solutions for the growing mobile device market.

Will Biometrics Replace NYC Doormen?

2010-03-16T11:32:00.004-04:00

Yesterday’s New York Post featured a story about a security company – Kent Security Services – that is marketing a “biometric” door for NYC apartment buildings. The door, which incorporates both facial and voice recognition technology, costs $15,000.

According to the article, the biometric door works as follows:

When a resident approaches the door to their building, a facial recognition camera captures a “sample” image, which is then compared to their “base” image in the database. If the images match, the door is unlocked for the resident.

If the facial images don’t match, the resident is prompted to say their name and where they are going. A “sample” voiceprint is captured through this process. If the “sample” voiceprint matches the resident’s “base” voiceprint, the door is unlocked. If there is no match, the resident is subject to further remote verification by central security staffers.

On February 22nd, I wrote about an Israeli company, FST21 Ltd., that is offering a similar technology.

Voice Biometrics Basics: Multi-Factor Authentication

2010-03-15T15:45:00.002-04:00

Multi-factor authentication is the process of using more than one factor to authenticate a person’s identity. The three categories are:

• Something the person knows (e.g., password or PIN)
• Something the person has (e.g., security token, smartcard, cell phone)
• Something the person is (e.g., biometric such as voiceprint)

Combining two or more factors, where one of the factors is a biometric, provides the strongest level of authentication. For example, passwords or PINs can be shared, observed or broken. Smartcards or cell phones can be lost or stolen.

U.S. Secret Service on Identity Theft

2010-03-12T13:23:00.009-05:00

Last night, I attended a seminar on "Identity Theft" presented by a U.S. Secret Service Special Agent. According to Javelin Strategy and Research (Wall Street Journal -- 2/10/2010), identity-theft is on the rise in the U.S. A record 11.1 million adults, up 12% from 2008, were victims. The total cost was $54 billion, up 12.5% from 2008.

The agent covered a number of topics including: how fraudsters get personal information, how fraudsters use that information, what to do if personal information is stolen and, finally, how to safeguard personal information.

How Fraudsters get Personal Information

According to the Secret Service, some of the methods used by fraudsters to get personal information are:

• Stealing mail (e.g., credit card statements, tax information, etc.)
• Rummaging through trash
• Bribing employees who have access to personal information
• Hacking databases containing personal information
• Stealing personal information from a place of work
• Obtaining a person’s credit report by posing as their landlord, employer, etc.
• Stealing card numbers by capturing data in an electronic “skimming” device
• Stealing wallet or purse
• Breaking into a home to steal personal information
• “Phishing” for personal information via email

How Fraudsters use Personal Information

According to the Secret Service, some of the ways fraudsters use personal information are:

• Call credit card issuers to change victim’s billing address
• Open new credit cards in victim’s name
• Establish new phone service in victim’s name
• Open a bank account in victim’s name and write bad checks
• Counterfeit checks or credit cards in victim’s name
• Authorize electronic transfer of victim’s funds
• File for bankruptcy in victim’s name to avoid debts fraudster incurred using victim’s name
• Taking out a loan in victim’s name
• Seeking employment in victim’s name
• If arrested, giving victim’s name to police

What to do if Personal Information is Stolen

According to the Secret Service, the following four immediate steps should be taken if personal information is stolen:

• Review and place a fraud alert on credit reports
• Close all accounts that may have been tampered with or opened fraudulently
• File a police report
• File a complaint with the Federal Trade Commission

How to Safeguard Personal Information

According to the Secret Service, these are some of the ways to safeguard personal information:

• Setup “strong” passwords for all accounts (e.g., avoid easily available information)
• Secure personal information at home
• Be vigilant when providing personal information on the phone, through email, etc.
• Deposit outgoing mail at post office and remove mail from mailbox promptly
• Shred personal information before placing in trash
• Don’t carry Social Security Card
• Limit amount of identification information and credit/debit cards when going out
• Install virus protection software
• Don’t open files sent by strangers
• Don’t store financial information on laptops
• Delete personal information from computers before disposing

After the presentation, the agent and I spoke about how voice biometrics can help stem the rising tide of U.S. identity theft and fraud. For example, financial institutions could deploy voice biometrics in their call centers. Fraudsters who obtained a victim’s personal information (e.g., mother’s maiden name, date of birth, etc.), would be thwarted when they are prompted to provide a sample voiceprint (which would then be compared to the victim’s base voiceprint). Also, credit card companies could require voice biometrics identity verification, at point of purchase, for certain transactions. These are just some of the ways that voice biometrics could be used to reduce identity theft related crimes.

Voice Biometrics Case Study - Vodafone Turkey

2010-03-10T13:07:00.004-05:00

In June 2009, Vodafone Turkey, that country’s second largest mobile communications provider (16 million+ subscribers), in concert with implementation partner SPEECHOUSE, began deploying a customer-facing voice biometrics application. Vodafone Turkey’s “Voice Signature” application is powered by PerSay’s VocalPassword™.

According to PerSay, the primary drivers for Voice Signature were to enhance customer service and improve security. Subscriber benefits include the ability to perform secure self-service transactions such as resetting a blocked mobile device. Enrollment in the Voice Signature application is voluntary.

Vodafone Turkey also benefits by a reduction in call center costs. According to them, thanks to Voice Signature, call durations decreased by about 15%, while customer satisfaction increased 85%.

As a testament to their voice biometrics implementation, Vodafone Turkey won “The Best Technology Solution” award at the “Istanbul Call Center Awards 2009” ceremony.

NC State Professor Streamlines Voice Biometrics Verification Process

2010-03-09T12:55:00.012-05:00

Dr. Robert Rodman, a professor of computer science at North Carolina State University, claims to have enhanced the text-independent voice biometrics verification process, according to a press release on the school’s Website. He believes that the verification process take too long for voice biometrics to gain widespread acceptance. To address the issue, Dr. Rodman assembled an international team of researchers who were able to modify existing computer models to streamline text-independent voice biometrics verification response times.

Dr. Rodman’s research, “Joint Frame and Gaussian Selection for Text Independent Speaker Verification,” will be presented at the International Conference on Acoustics, Speech and Signal Processing (ICASSP) in Dallas, March 14-19.

Stay tuned for more on this topic.

Voice Biometrics Case Study – TD Waterhouse Canada

2010-03-08T11:37:00.003-05:00

In 2008, TD Waterhouse Discount Brokerage Canada launched a client-facing voice biometrics application. The service, dubbed “Voice Print System,” is powered by Nuance Verifier™. According to TD Waterhouse’s Website, the Voice Print System provides the following benefits to clients:

• Enhanced convenience and speed – automates verification of client’s identity allowing quicker access to their accounts and transactions
• Improved security – voice biometrics verifies that the client is who they claim to be

Enrollment Process:
• Client calls TD Waterhouse’s contact center and, when prompted, says “I’m not enrolled.” The client’s identity is manually verified by a rep, who also explains the Voice Print System. The client is then connected to the enrollment system
• Client is prompted to speak their phone number
• Client is prompted to say the phrase “my voice is my password”
• Client is prompted to speak a secret date (month & date), as well as a hint
• This process creates the client’s “base” voiceprint and stores it in the database for future use

Verification Process:
• Clients call the TD Waterhouse contact center and, when prompted, say their phone number and secret date. This process creates the client’s “sample” voiceprint which is then compared to their “base” voiceprint in the database. If the voiceprints match, the client’s identity is verified

According to Nuance, most TD Waterhouse clients have elected to participate in the Voice Print System service. This may be due in part to their personalized approach of having a rep explain the process to clients. The Voice Print System has also allowed TD Waterhouse to reduce agent talk time by 30+ seconds.

Voice Biometrics Case Study - Bell Canada

2010-03-05T12:42:00.013-05:00

In 2007, Persay and IBM Global Services Canada began the rollout of the first large-scale customer-facing voice biometrics system. It is only fitting that the client was Bell Canada. After all, in 1867, Alexander Graham Bell’s father began work on developing an early voiceprint.

Bell is Canada’s largest communications company. According to Persay’s Website, the principal project driver for Bell was to fight identity theft and make the privacy protection (i.e., verification) process more convenient for customers.

Enrollment process:
• Customer calls Bell’s contact center and is presented with the option to enroll using an IVR system
• If the customer opts in, the enrollment process is initiated. Or, if the customer opts out, they can ask for a re-prompt to enroll in 60 days
• Customer enrolls by repeating a pass phrase “At Bell, my voice is my password” three times (process takes approximately 2 minutes). The captured “base” voiceprint is stored in the database for future verification
• The enrollment is secured by the customer’s PIN and an account number and they are notified (via callback or SMS) when the enrollment process is completed

Click here for a demo.

Verification process:
• In subsequent calls to Bell’s contact center, the customer is prompted to repeat their “At Bell, my voice is my password” pass phrase. The captured “sample” voiceprint is then compared to the customer’s “base” voiceprint
• If the voiceprints match, the customer is successfully verified and is automatically granted access to the IVR or a live agent (who is alerted that the customer’s identity has already been verified – saving time)
• Customer can add multiple voiceprints per account to enable access for additional authorized co-users (e.g., spouse)

Click here for a demo.

To date, more than 2,000,000 Bell Canada customers have voluntary enrolled and verification rates exceed 4,000,000 a year.

Updated Voice Biometrics Market Forecast through 2014

2010-03-04T14:49:00.010-05:00

Yesterday, I posted projections for the global voice biometrics market (2009-2011). Derek Top, of Opus Research, was kind enough to send me a revised forecast covering the years 2008-2014.

As you can see from the chart, the market is expected to grow from $124 million (2009) to $260 million (2014). This represents a compounded annual growth rate of approximately 16%. According to the chart, the steepest growth is expected to occur between 2010-2011. So let's make this the year of voice biometrics!

Voice Biometrics Basics – Metrics

2010-03-04T10:58:00.004-05:00

There are several metrics used to measure the success of a voice biometrics system:

• Enrollment rate – % of authorized users who successfully enrolled (i.e., “base” voiceprint captured)
• Verification rate - % of authorized users who are successfully verified (i.e., “sample” voice print captured and matched against “base” voiceprint)
• False acceptance rate (FAR) - % of unauthorized users who are accepted by the system. Also known as false positive or type I error.
• False rejection rate (FRR) - % of authorized users who are rejected by the system. Also known as false negative or type II error.
• Crossover error rate (CER) – point of intersection when FAR and FRR are plotted against each other (i.e., FAR = FRR). In general, the lower the CER the better.

It’s a fine art to tune a voice biometrics system to achieve simultaneously low FARs (i.e., keeping the unauthorized folks out) and low FRRs (letting the authorized folks in).

Voice Biometrics Market Projections (2009–2011)

2010-03-03T09:59:00.004-05:00

According to ThirdFactor, Opus Research predicts the voice biometrics market will grow from $139.4 million (2009) to $225.8 million in 2010, to $260.1 million in 2011. This represents a substantial 62% increase 2009-2010, but only a 15% increase 2010-2011.

I’m puzzled by the % growth decrease (i.e., 62%-->15%) projected for next year. I would expect % growth to continue increasing once voice biometrics systems gain momentum in the marketplace.

What say you?

Voice Biometrics Basics – Verification

2010-03-02T15:51:00.005-05:00

Verification is the process of comparing a person’s “sample” voiceprint to their “base” voiceprint obtained during the enrollment process. If the voiceprints match, based on a probability score, the person’s identity is verified.

Text-dependent voice biometrics systems require a person to speak the same pass phrase(s) during enrollment and verification. Text–independent systems do not. The person can be asked to repeat a series of random pass phrases to capture a “sample” voiceprint. Or, the “base” and “sample” voiceprints can be obtained in the background – even without the person’s knowledge (ideal for forensic applications).

My Neighbor Secures Mobile Commerce Transactions with Voice Biometrics

2010-03-01T12:12:00.005-05:00

Planet Payment, a multi-currency payment and data processor, based in Long Beach, NY, has deployed a mobile shopping application which uses voice biometrics to secure transactions. The product is called “Shop BuyVoice™’ and it enables shoppers to purchase items securely, from registered “Voice Store” merchants, over the phone.

According to their Website, Planet Payment works with merchants to set up their mobile commerce (“Voice”) stores. Shoppers also need to enroll and provide a “base” voiceprint. Enrolled shoppers can see a product in an ad, browse a storefront after hours, or respond to an in-store display, then call Shop BuyVoice and buy the item simply by saying the product code and verifying their identity (i.e., by entering their phone number and providing a “sample” voiceprint). Click here for a demo.

Another step closer to making voice biometrics a commercial reality.

Voice Biometrics Basics - Enrollment

2010-02-28T09:54:00.002-05:00

Enrollment is the process of creating a “base” voiceprint for a person. Typically, the person (after their identity is verified) will be prompted to repeat a pass phrase three times. For example, “my voice is my password.” The voice biometrics system captures the person’s data and converts it to a “base” voiceprint. The “base” voiceprint is stored in a database for future use (i.e., identity verification).

Voice Biometrics Basics: Voiceprints

2010-02-27T09:50:00.009-05:00

A voiceprint is a mathematical representation of the physical characteristics of a person’s vocal tract (shape and motion patterns). A voiceprint is not an audio recording of a person’s voice.

Components of a Vocal Tract

• Nasal cavity
• Palate
• Soft palate vellum
• Uvula
• Tonsils
• Tongue
• Pharynx
• Epiglottis
• Vocal cords (glottis)
• Larynx
• Esophagus
• Thyroid cartilage
• Hyoid
• Lower jaw
• Lips
• Teeth
• Alveolar ridge
• Upper gums (alveolus)

Voiceprints are unique to each person (similar to fingerprints). A person's identity can be verified by matching a “sample” voiceprint with a “base” voiceprint.

Certified Biometrics Professional Programs

2010-02-26T11:13:00.006-05:00

In yesterdays posting, I wrote that several colleges are offering degrees in biometrics. Today, I'd like to make you aware of two options for obtaining certification in biometrics (Note: this is not an endorsement of either program).

The first program, sponsored by the Institute of Electrical and Electronics Engineers, Inc. (IEEE), leads to the designation “Certified Biometrics Professional™.” According to the Website, “to earn the IEEE CBP credential, candidates must pass one rigorous, multiple-choice examination. Individuals who earn the CBP credential will be required to maintain their knowledge and skills by participating in continuing education and professional development activities.”

The exam covers the following topics:

• Biometrics Fundamentals
• Biometric Modalities
• Biometric System Design and Evaluation
• Biometrics Standards
• Social, Cultural and Legal Implications
• Biometrics Applications

Exams are given during two 1-month testing periods. Total fees are $495 for IEEE members and $595 for non-members.

The second program, offered by the Certified Biometrics Security Professional Institute, leads to the designation “Certified Biometrics Security Professional,” “Certified Biometrics Security Engineer” or “Certified Biometrics Solutions Developer.”

The “Certified Biometrics Security Professional” exam covers the following topics:

• Introduction to Biometrics
• Type of Biometrics
• Why Biometrics
• Usage of Biometric Technologies
• Biometrics In Operation
• Biometrics Standards
• Comparison
• Smart Cards
• Multistage Authentication With Biometrics
• Integrating Biometrics with other Technologies
• Privacy and Confidentiality Issues and Concerns
• Biometrics and Security Compliances
• Security Issues
• Basic Biometric Lifecycle
• Risks associated with users of Biometrics systems

Fees start at $995.

I’d be interested to hear if any of you have received any of these certifications.

Looking for a Degree in Biometrics?

2010-02-25T11:47:00.005-05:00

Several colleges in the U.S. are now offering degree programs in biometrics. For example, Davenport University and West Virginia University both offer four-year programs.

Biometrics courses offered at Davenport include:
• Biometrics Fundamentals
• Applicable Biometrics
• Biometric Spoofing
• Information Warfare and Security
• Authentication and Audits
• Biometric ID and Privacy Laws
• Credential Hardening
• Biometric Security Architectures
• Advances in Biometric Technologies

West Virginia University appears to be a hub for biometrics research. According to their Website, they house the Center for Identification Technology Research and are the lead academic partner for the FBI’s Biometric Center of Excellence.

Back to school anyone?

Books on amazon.com that Reference Voice Biometrics

2010-02-24T08:20:00.003-05:00

Believe it or not, there are 55 books listed on amazon.com that reference voice biometrics. The books range from the very technical to the self-effacing "Biometrics for Dummies." Many of the books look interesting and I look forward to the opportunity to review some of them in the near future.

If you have read any of the books, please feel free to post your comments.

Automated Speaker Verification (Voice Biometrics) - What's Everyone Waiting For?

2010-02-23T14:55:00.002-05:00

Automated speaker verification uses voice biometrics to verify a caller’s identity by his or her spoken voice. Voice biometrics measures the person’s vocal tract characteristics (to produce a digitized voiceprint), and is unique to each individual. Voice biometrics is highly accurate, non-invasive and ideal for identity verification over the phone.

Automated speaker verification consists of two processes -- enrollment and verification.

Enrollment:
• Person enrolls (after their identity is verified) by repeating a pass phrase three times (text-dependent approach)

Verification:
• In subsequent calls, enrolled person is prompted by IVR to repeat their pass phrase
• Successful verification allows person to proceed in IVR or transfer to an agent (who is alerted to person’s verification status)

There are four compelling reasons why automated speaker verification should be deployed at call centers:

• Reduces costs
• Increases security
• Enhances customer experience
• Facilitates regulatory compliance

Reduces Costs

In today’s environment, most call centers ask callers a series of challenge questions (e.g., “mother’s maiden name”) to verify their identity. This process typically takes anywhere from 30-60 seconds. Automated speaker verification can do it in less than 5 seconds. Multiply the savings by 100s/1,000s of callers and the productivity gains start to add up. Of course, automating the identity verification process also allows agents to spend more valuable time actually servicing callers.

Increases Security

Identity fraud continues to be a growing problem for consumers and businesses in the United States. Through the use of social engineering techniques such as “pre-texting” or “phishing,” fraudsters can obtain personal information that allows them to assume the identity of another person. This is of particular concern to call centers, as a caller may know the answers to the challenge questions but in fact be an imposter. Automated speaker verification can significantly reduce this threat by ensuring that the caller is actually who they say they are.

Enhances Customer Experience

“Please verify your address.” “What was the name of your first dog?” “Who did you date in fifth grade?”

Automated speaker verification provides a quicker and more user-friendly process for verifying a caller’s identity. For starters, there is no need for the caller to remember or disclose personal information in response to all those annoying challenge questions. Callers get to the service or information they need quicker and spend less time on the call – and that’s a good thing!

Facilitates Regulatory Compliance

Regulations such as FFIEC and HIPAA mandate higher levels of identity verification, known as multi-factor authentication. The three primary factor categories are “something the caller knows” (e.g., account number), “something the caller has” (e.g., hardware token) and “something the caller is” (e.g., person’s voice characteristics). Call centers can use automated speaker verification, combined with another factor (such as account number), to ensure compliance with the multi-factor requirement.

Conclusion

Automated speaker verification is a proven technology which can reduce costs, increase security, enhance the customer experience and facilitate regulatory compliance.

What's everyone waiting for?

Israeli Company Secures Buildings with Voice Biometrics

2010-02-22T16:25:00.002-05:00

An Israeli technology company, FST21 Ltd., has developed a unique product ("SafeRise") which combines facial recognition, behavioral patterns and voice biometrics to secure multi-tenant buildings. The application, developed for use by the Israel Defense Force, would replace the need for keys, access cards or codes. Instead, the authorized person would be granted access once their biometric characteristics are verified

According to their Website, FST21 is targeting real estate developers, property management companies, building systems integrators, contractors and architects. SafeRise was installed at a luxury apartment complex (300 units) in Israel at a cost of $100,000.

Very impressive!

Star Trek meets Voice Biometrics?

2010-02-21T12:09:00.003-05:00

I recently found what appears to be an obsolete Website page that described a cool voice biometrics product for the consumer market. The application -- "Star Trek: Deep Space Nine Voice Print Security Program" -- was designed to secure home desktops/laptops, and Windows applications, using voice biometrics. The user enrolled their base voiceprint and were granted access if their sample voiceprint matched. If the voiceprints didn't match, the user was rejected and a Star Trek "red alert" shield was displayed along with the "Warning! Intruder alert. Unauthorized user - access denied" sound effect. The Company claimed 99% accuracy.

Countering Voice Biometrics Hacking

2010-02-20T17:21:00.005-05:00

Whenever I give a presentation on voice biometrics, invariably, someone in the audience will bring up the 1992 movie “Sneakers.” You may recall that the main character is able to successfully hack a voice biometrics system by recording the authorized individual and splicing together the pass-phrase “my voice is my password.” Of course, this reference always leads to spirited discussion about the risks of hacking voice biometrics.

Fortunately, there are several methods to counter hacking of voice biometrics systems. In an interview with Canadian Security Magazine, I discussed one such approach. It involves asking users to repeat a series of words or numbers during the enrollment process. When the user subsequently accesses the system, they are prompted to repeat a randomly generated sequence of words or numbers. This method works well, as it’s improbable that a hacker would know the random sequence of words or numbers the user will be asked to repeat.

Voice Biometrics Goes to War

2010-02-19T12:06:00.003-05:00

Some of the earliest voice biometrics applications were designed for military use. There are multiple ways for the military to deploy voice biometrics. For example, voice biometrics can be used to remotely verify the identity of forward air controllers (these are the folks that direct aircraft to attack enemy positions) when they call in an air strike. Imagine what would happen if an unauthorized individual (e.g., enemy combatant) gains access to the secure forward air controller channel and directs aircraft to attack the good guys. The results would be catastrophic.

I'm sure that there are many other top-secret uses of voice biometrics under consideration by the military. The good news for our industry is that technology that has its origins in military applications often ends up in widespread civilian use.

Voice Biometrics Conference - May 4-5, 2010

2010-02-18T18:08:00.003-05:00

In 2007, I attended the first-ever Voice Biometrics Conference, presented by opusresearch, in Washington, DC. It was an excellent opportunity to meet and compare notes with every major voice biometrics player in the world.

This year's Voice Biometrics Conference will be held May 4-5 at the Hyatt Regency Hotel in Jersey City, New Jersey. The conference agenda and speakers look first-rate and I highly recommend those interested in voice biometrics attending. I definitely plan to be there and I look forward to meeting all of you.

Registration details are available by clicking here.

Voice Biometrics Enables Mobile Banking

2010-02-17T11:49:00.003-05:00

According to an article on TMCnet.com, mobile banking is growing rapidly. Voice biometrics is playing a major role preventing identity fraud and ensuring the security of transactions. One company, VoiceCash Bank is pioneering the delivery of global money transfers, via mobile banking, to millions of expatriate workers throughout the world. The process works as follows:

All customers enroll by providing a base voiceprint which is linked to their mobile phone number
Whenever a customer processes a transaction involving a transfer of funds, the automated system calls the customer's mobile phone and asks them to provide a sample voiceprint
If the voiceprints match, the customer is positively identified and the transaction goes through

This is a very exciting application for voice biometrics!

Who are You? Voice Biometrics Knows for Sure!

2010-02-15T08:56:00.005-05:00

Most contact centers rely on a combination of "challenge questions" to verify a caller's identity. Examples of commonly asked questions follow:

What is your mother's maiden name?
What is your address, phone number?
What are the last 4 of your Social Security number?
What is the name of your favorite childhood friend?
What street did you live on growing up?
What was the last name of your favorite childhood teacher?
In what city or town was your first job?
What was the name of your elementary / primary school?
What is the street number of the house you grew up in?
What was the make and model of your first car?
What is the your pet's name?
What is your favorite team?
What is your favorite movie?
In what city were you born?
What is your favorite color?

Contact center agents can't assume that the caller answering the challenge questions correctly is actually who they say they are. For example, the fraudster may be an immediate family member (as shocking as that sounds!) who knows all the answers. Only voice biometrics can positively verify the caller's identity!

Voice Biometrics Can Help Stem the Rising Tide of U.S. Identity-Theft

2010-02-14T09:13:00.003-05:00

Identity-theft is on the rise in the U.S., according to recent study by Javelin Strategy and Research (Wall Street Journal -- 2/10/2010). A record 11.1 million adults, up 12% from 2008, were victims. The total cost was $54 billion, up 12.5% from 2008. The article goes on to say that incidents of identity-theft show no signs of decreasing in the foreseeable future.

Voice biometrics can help stem the rising tide of U.S. identity-theft. For starters, financial institutions could deploy voice biometrics in their call centers. Fraudsters, who may have stolen the answers to challenge questions (e.g., mother’s maiden name, date of birth, etc.), would be thwarted when their sample voiceprint is compared to the identity-theft victim’s base voiceprint. Our phones should be ringing off the hook!

Voice Biometrics Monitors Persons on House Arrest, Parole or Probation

2010-02-13T11:21:00.002-05:00

Yesterday, we discussed how voice biometrics can be deployed to monitor inmate phone calls from prison. Another related application, is the use of voice biometrics to ensure that persons on house arrest, parole or probation are where they should be, when they say they are. The current approach is to use ankle bracelets to monitor these individuals. However, there is always the potential for these bracelets to be removed and placed on another person or object – rendering them worthless.

The voice biometrics process works as follows. A person who needs to be monitored at home is required to have a land line phone, and provide a base voiceprint. When the person is required to be at home, an automated system calls them, at scheduled or random intervals, and requests a sample voiceprint. If the sample voiceprint matches the base voiceprint, the system is able to verify that the correct individual is where, and when, they should be.

To those of us with teenagers, I can think of some additional applications!

Voice Biometrics Goes to Prison

2010-02-12T11:17:00.002-05:00

One of the more unusual applications of voice biometrics is the identification of prison inmates when they make a call. Correctional institutions are required to track all calls made by inmates to prevent and apprehend illegal activity. In most cases, inmates are assigned a calling PIN which they are required to use when they make calls. Some inmates “share” their PIN (voluntarily or involuntarily) with other inmates making it near impossible to accurately track who actually made the call.

Voice biometrics is able to ensure that the inmate making the call is who they say they are. When the inmate first arrives at prison, they provide a base voiceprint. Each time they make a call, their sample voiceprint is compared to their base voiceprint. If they match, the inmate is able to complete their call. Another benefit is the elimination "PIN sharing" -- which increases prison safety.

New Hampshire Seeks to Ban Use of Voice Biometrics

2010-02-11T15:15:00.005-05:00

According to an article in SC Magazine, New Hampshire’s Legislatures is considering a bill that, if enacted, would profoundly affect the voice biometrics industry. The bill “would ban the use of ID devices or systems that require the collection or retention of an individual's biometric data” --including, voice biometrics.

New Hampshire claims to be acting out of concern for their citizen’s “privacy.” The fuss all started in 2008, when Bank of America began requiring non-customers to provide a fingerprint as identification, according to the Nashua Telegraph. Bank of America has since rescinded its policy.

New Hampshire is not the first state to consider banning the use of biometrics (including voice), nor will it be the last. Privacy concerns are a serious issue -- with many organizations frightening the public into believing that voice biometrics takes us one step closer to the Orwellian World depicted in “1984.” The voice biometrics industry must continue to address all real and imaginary privacy concerns. I'll have more to say about this in the near future.

Voice Biometrics Prevents Time and Attendance Fraud

2010-02-10T16:36:00.000-05:00

Voice biometrics can be deployed to prevent remote employee time and attendance fraud. One of my former clients managed several group homes which were staffed round-the-clock. The client wanted to ensure that the correct employee was on-site when scheduled. Unfortunately, there had been a history of fraud; for example, time card starting/ending times were falsified, etc.

I proposed a solution using voice biometrics. At the start and end of each shift, the group home employee would be required to call an IVR and verify their identity (i.e., provide sample voiceprint). The system was also able to detect the phone number (i.e., group home) the employee was calling from. Problem resolved -- time and attendance fraud eliminated!

Voxeo’s Announcement

2010-02-09T08:55:00.001-05:00

Today’s announcement that IVR provider Voxeo will partner with four voice biometrics vendors (CSIdentity, Persay, TradeHarbor and Vocalect) has promise. It offers 100,000 telephony/Web developers, who use Voxeo’s IVR developer portal, the opportunity to develop creative voice biometrics applications for their clients. This move has the potential to mainstream the use of voice biometrics in organizations large and small. The one thing I’m unclear about is how the developers are going to differentiate between the voice biometrics applications offered by the four vendors. Time will tell.

Speech Recognition vs. Speaker Recognition

2010-02-08T13:22:00.003-05:00

People often get confused between speech recognition and speaker recognition. Let’s explore the difference.

Simply stated, speech recognition is the ability to recognize what a person is saying. Speaker recognition on the other hand is the ability to identify the person speaking.

Speech recognition has been in use for decades. Today, many organizations have replaced live agents with automated interactive voice response (IVR) systems. The IVRs may prompt users to speak their entries. For example, when calling directory assistance, users are prompted to speak the name of the individual or business that they are inquiring about. The system converts the spoken phrases to text, recites them back to the user for verification, and searches the database for a match.

Speaker recognition is a relatively new technology. Using voice biometrics, a speaker recognition system is able to identify, or verify the identity, of a person who has previously enrolled (i.e., provided a base voiceprint) in the system. A voiceprint is a stored set of measurable characteristics of a human voice that are unique to each individual. A sample voiceprint can be compared to a base voiceprint to identify, or verify the identity, of a person. Speaker recognition is an ideal way to verify the identity of a person remotely (e.g., performing a financial transaction via telephone).

Speaker Verification vs. Speaker Identification

2010-02-07T09:45:00.003-05:00

Voice biometrics applications can be classified as speaker verification or speaker identification. Let’s examine the difference.

Speaker verification is a one-to-one process of confirming the identity of an enrolled person. The person provides a sample voiceprint which is compared to their base voiceprint in the database. If the voiceprints match, the person’s identity is verified (accepted), if they don’t match, the person’s identity is not verified (rejected). Most commercial applications are classified as speaker verification.

Speaker identification is a one-to-many process of determining the identity of an unknown person. The person provides a sample voiceprint which is compared to all of the base voiceprints in the database. If there is a match, the person is identified; if there is no match, the person is not identified. Speaker identification has been successfully used in law enforcement and intelligence applications.

Article about Voiceprints in Life Magazine - September 28, 1962

2010-02-06T15:17:00.007-05:00

On September 28, 1962, Life Magazine published the following fascinating article about voiceprints:

"Device picks Jack from all the pack"

"The Kennedy mimics may sound just like the President to people, but they do not fool a highly sensitive machine which makes voice-prints that may be as infallible in identifying individuals as fingerprints are. The device was developed by Bell Telephone for a very serious purpose: to help law-enforcement agencies identify persons who have been heard but not seen. The tape of a voice, perhaps recorded on the phone or by wiretapping, is fed to a stylus which transcribes electronic impulses into squiggly graphs. The squiggles trace volume, resonance and pitch which are never the same for any two people. As the voice-prints at left and below show, the machine can unmask even the cleverest of imitators."

An accompanying caption mentions that the voiceprint technique was created by Dr. Lawrence Kersta of Bell Laboratories. Check out this video.

Early History of Voice Biometrics

2010-02-05T09:53:00.002-05:00

Most people think of voice biometrics as a relatively new technology. However, according to a 2004 article by Lisa Myers (SANS Institute), the history of voice biometrics actually began in 1867. At that time, Alexander Graham Bell’s father began work on developing an early voiceprint. Jumping ahead to World War 2, the same article mentions the pioneering work by Bell Telephone Labs on spectrograms. The concept was to identify a specific enemy’s voice and track their movements by the location of their radio transmissions. Apparently, the technology did not work very well.

Fast forward two decades. According to the National Science and Technology Council, in 1960, a Swedish professor, Gunnar Fant, published a ground-breaking model describing the physiological components of acoustic speech production. Fant’s model was expanded in 1970, by Dr. Joseph Perkell, to include the tongue and jaw. In 1976, Texas Instruments developed a prototype voice biometrics system that was tested by the United States Air Force and Mitre Corporation. Voice biometrics was on its way!

Why are Help Desk Agents Still Resetting Passwords?

2010-02-04T12:47:00.003-05:00

I’ve seen estimates that 40%+ of help desk transactions are password reset related. Voice biometrics can enable users to reset their own passwords without help desk intervention. Automated self-service password reset applications provide significant benefits to the IT organization, including:

1) Reduces costs – no need for live agent
2) Improves service – available 24/7, never a wait for a live agent and faster service
3) Increases security – voice biometrics is more secure than challenge questions to verify a user’s identity questions

Automated password resets is a relatively simple process. The user calls the help desk IVR, selects the password reset option, enters one factor of authentication (e.g., account number) and validates their identity by providing a voiceprint sample. Once the user's identity is verified, the system generates a new password and either emails or speaks it over the phone.

Three Good Reasons Why Call Centers Should Use Automated Speaker Verification

2010-02-03T08:27:00.006-05:00

Call centers should all be using automated speaker verification (voice biometrics) in conjunction with their IVR systems. Here are three reasons why:

1) May reduce operating costs (e.g., eliminates the need for agent-led, manual verification of callers -- savings of 20-40 seconds per call)
2) Improves customer service (gets the caller to the service or information they need quicker)
3) Enhances security (reduces potential fraud due to social engineering)

Also, financial institutions and health care providers can satisfy multi-factor compliance by using voice biometrics.

Voice Biometrics – Text-Dependent vs. Text-Independent

2010-02-02T10:18:00.002-05:00

Voice biometrics systems come in two flavors: text-dependent and text-independent.

Let’s explore the difference…

Text-dependent systems require a person to speak the same pass phrase(s) during enrollment and identity verification. The system compares the base voiceprint from enrollment with the sample voiceprint from verification. The majority of voice biometrics systems are text dependent.

Text–independent systems do not require a person to speak a specific pass phrase during enrollment and verification. The base voiceprint and sample voiceprint can be obtained in the background – even without the person’s knowledge (ideal for forensic applications). Text-independent systems usually require a longer enrollment process to ensure verification accuracy.

Advantages of Voice Biometrics

2010-02-01T14:12:00.004-05:00

Before reviewing the advantages of voice biometrics over other biometrics (fingerprints, etc.), let’s take a quick look at the advantages of using any biometric to verify a person’s identity:

1) Only biometrics can verify that a person is actually who they claim to be
2) Passwords can be: forgotten, shared, observed and broken
3) Security tokens (smart cards, etc.) can be: lost, stolen, duplicated (some) and forgotten

Voice biometrics compared to other biometrics is:

1) User-friendly - speaking is natural and requires no special effort
2) Cost effective - verification is accomplished via telephone or microphone
3) Convenient - enables remote verification of a person’s identity
4) Secure – highly accurate

Measuring the Accuracy of Voice Biometrics

2010-01-31T12:25:00.001-05:00

One question that frequently arises is the accuracy of voice biometrics. Organizations want to ensure that the voice biometrics application will prevent the bad guys from getting in, while at the same time, ensuring that the good guys can get in.

Basically, voice biometrics accuracy is measured by two factors:
1) False acceptance rate (FAR) – unauthorized person is accepted
2) False rejection rate (FRR) – authorized person is rejected

FAR and FRR can be plotted against each other. The point of intersection is known as the crossover error rate (CER). It should be obvious that the lower the CER the better.

It’s a fine art to tune voice biometrics applications to achieve simultaneously low FARs (i.e., keeping the unauthorized folks out) and low FRRs (letting the authorized folks in).

Securing a Website with Multi-factor Authentication and Voice Biometrics

2010-01-29T15:50:00.000-05:00

In the example below, “XYZ, Inc.” has decided to secure a Website using multi-factor authentication and voice biometrics:

• “XYZ, Inc.” generates account IDs to all users and provides this data to its voice biometrics provider
• New users enroll by calling an assigned phone number, entering their account ID and repeating a pass-phrase three times (this process creates a “base” voiceprint)
• On subsequent Website visits, the user calls the assigned phone number, enters their account ID and repeats the pass-phrase once (this process creates a “sample” voiceprint)
• The user’s “sample” voiceprint is compared to the “base” voiceprint
• If the voiceprints match, the user is enabled to access the Website. If the voiceprints don't match, the user is directed to an alternate business process (e.g., help desk).

Answers to Some FAQs

2010-01-29T12:55:00.003-05:00

What is biometrics?
Biometrics is the measurement of a person’s physical and/or behavioral characteristics, such as fingerprints, iris scans, or voiceprints, to verify their identity.

What is voice biometrics?
Voice biometrics is the measurement of a person’s unique voice characteristics, or voiceprint, to verify their identity.

What is a voiceprint?
A voiceprint is a stored set of measurable characteristics of a human voice that are unique to each individual. No two individuals have the same exact voiceprint. Voiceprints can be compared with each other to positively verify a person’s identity.

What is automated speaker verification?
Automated speaker verification is the process of comparing a person’s voiceprint with a stored voiceprint to positively verify their identity. Automated speaker verification uses advanced voice biometrics technology.

Why use biometrics to verify a person’s identity?
Biometrics is the best way to verify that a person is actually the person.

Why use voice biometrics to verify a person’s identity?
Voice biometrics is an easy and natural way to verify a person’s identity. No special devices, such as readers or scanners, are required. The user simply needs access to a telephone or microphone.

Why aren’t User IDs and Passwords enough to verify a person’s identity?
Simply stated, there is no way that User IDs and Passwords can verify that a person is actually the person. In addition, User IDs and Passwords can be forgotten, shared, observed and broken.

Why not use tokens, such as smart cards, to verify a person’s identity?
Simply stated, there is no way that tokens can verify that a person is actually the person. In addition, tokens can be lost, stolen or forgotten.

What is multi-factor authentication?
Multi-factor authentication is the process of verifying a person’s identity using more than one validation factor. For example, something you know, such as User ID and Password, would be one factor. Something you are, such as a voiceprint, would be another factor.

What are the benefits of multi-factor authentication?
Multi-factor authentication greatly enhances the robustness of any security system. Even if one factor is compromised, the additional factor would still prevent security breaches.

Voice Biometrics Process

2010-01-28T10:29:00.000-05:00

The voice biometrics process is relatively simple...

Enrollment:

1. Person repeats a pass phrase three times (creates "base" voiceprint)
2. Base voiceprint is saved in the database

Verification:

1. Enrolled person repeats a pass phrase (creates "sample" voiceprint)
2. The "sample" voiceprint is compared to the "base" voiceprint
3. If the voiceprints match (based on a probability score), the person’s identity is verified
4. If the voiceprints don’t match, the person is directed to an alternate business process

Voice Biometrics Defined

2010-01-28T10:08:00.000-05:00

Voice biometrics is the measurement of the unique characteristics of an individual’s voice. These characteristics, which are based on an individual’s vocal tract shape and motion patterns, are converted into a mathematical formula known as a voiceprint. This is accomplished by acquiring a live voice sample from an individual and applying a specialized algorithm to convert the sample into a digitized "base" voiceprint.

The voice biometric identity verification process is conceptually similar to comparing fingerprints, and no two voiceprints are exactly the same. By comparing a "sample" voiceprint with the "base" voiceprint, one is able to positively verify the identity of any enrolled individual.