Speaker identification
From Free net encyclopedia
In computer science, speaker identification is the problem of identifying a person solely by their speech. It can be used for purposes such as police investigations and intelligence.
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 first is important for speech recognition software and the second for the purpose of biometrics, however recent evidence from linguistics has raised doubts about the security of using speaker identification as a means of user authentication.
Speaker identification is based on complex voice processing algorithms.
[edit]
References
- Elisabeth Zetterholm, Voice Imitation. A Phonetic Study of Perceptual Illusions and Acoustic Success. Phd thesis, Lund University. (2003)
[edit]