Speaker veriflcation flnds applications in many difierent ar- eas such as access control, transaction authentication, law enforcement, speech data management and personalization. As for other biometric technologies the prime motivation of speaker recognition is to achieve a more usable and reliable personal identiflcation than by using artifacts such as keys, badges, magnetic cards or memorized passwords. Speaker veriflcation technologies are often ranked as less accurate than other bio- metric technologies such as iris scan or flngerprints. However, there are two main factors that make voice a compelling biometric. First, there is a proliferation of automated telephony services for which speaker recog- nition can be directly applied. Second, talking is a very natural gesture, often considered as lowly intrusive by users as no physical contact is requested. These two factors, added to the recent scientiflc progresses, made voice biometric converge into a mature technology.
[1]
Biing-Hwang Juang,et al.
Fundamentals of speech recognition
,
1993,
Prentice Hall signal processing series.
[2]
Louis-Jean Boë,et al.
Forensic voice identification in France
,
2000,
Speech Commun..
[3]
Douglas A. Reynolds,et al.
A Tutorial on Text-Independent Speaker Verification
,
2004,
EURASIP J. Adv. Signal Process..
[4]
Joseph Picone,et al.
Signal modeling techniques in speech recognition
,
1993,
Proc. IEEE.
[5]
Douglas A. Reynolds,et al.
Speaker Verification Using Adapted Gaussian Mixture Models
,
2000,
Digit. Signal Process..
[6]
Douglas A. Reynolds,et al.
An overview of automatic speaker recognition technology
,
2002,
2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.