Definitions
Speaker recognition (also known as voice recognition)
“ | is a biometric modality that uses an individual's voice for verification and/or identification. For recognition purposes, speaker recognition uses models developed from an individual's speech, a feature influenced by both the physical structure of an individual’s vocal tract and the behavioral characteristics of the individual. | ” |
“ | takes a voice sample of a user via the mobile device's microphone to identify and authenticate a user.[1] | ” |
Overview
Speaker recognition can be used to verify a person’s claimed identity or to identify a particular person. It is often where voice is the only available biometric identifier, such as telephone and call centers.
Speech recognition recognizes the words being said, and is not a biometric technology.
How it works
During enrollment, a speaker recognition system captures samples of a person’s speech by having him or her speak some predetermined information into a microphone or telephone a number of times. This information, known as a passphrase, can be a piece of information such as a name, birth month, birth city, or favorite color or a sequence of numbers. This is known as a "text-dependent system." "Text-independent systems" are also available that recognize a speaker without using a predefined phrase. Text-dependent systems perform more efficiently. Text-independent systems are more flexible and are more effective in situations where the individual may be unaware of the collection or unwilling to cooperate, or where spoofing is a concern.
The phrase or phrases are converted from analog to digital format, and the distinctive vocal characteristics, such as pitch, cadence, and tone, are extracted, and a speaker model is established. A template is then generated and stored for future comparisons. Voice templates are much larger than templates generated from other biometric technologies, typically 10,000 to 20,000 bytes.
Sources
- Information Security: Challenges in Using Biometrics, at 9.
- Privacy and Biometrics: Building a Conceptual Foundation, at 18-19.
See also
- ↑ NISTIR 8080, at 17.