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).
Sunday, January 31, 2010
Friday, January 29, 2010
Securing a Website with Multi-factor Authentication and Voice Biometrics
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).
• “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
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.
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.
Thursday, January 28, 2010
Voice Biometrics Process
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
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
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.
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.
Subscribe to:
Posts (Atom)
