Speaker identification
From Wikipedia, the free encyclopedia
In computer science, speaker identification (for another type of speaker recognition see speaker verification) is a type of speaker recognition. It is the problem of identifying a person solely by their voice. It can be used for purposes such as police investigations.
It is different from speaker verification in that, as an example, a criminal's voice is cross checked against a database of criminal's voices looking for a match, and ergo the identity. In contrast, speaker verification seeks to verify, as an example that you really are Mary, seeking to take money out of your bank account using a speaker biometric checking ATM.
Speaker identification problems generally fall into two categories:
- Differentiating multiple speakers when a conversation is taking place.
- Identifying an individual's voice based upon previously supplied data regarding that individual's voice.
The latter is in the scope of biometrics.
Speaker identification is based on complex voice processing algorithms. In contrast, speaker verification is based on more simple voice print comparing.
[edit] References
- Elisabeth Zetterholm, Voice Imitation. A Phonetic Study of Perceptual Illusions and Acoustic Success. Phd thesis, Lund University. (2003)
