ON WORD BOUNDARY DETECTION IN DIGIT-BASED SPEAKER VERIFICATION

In an automatic speaker verification (ASV) system with prompted passwords, we use vocabulary-dependent hidden Markov models and rely on the ability to explicitly locate the corresponding words and their boundaries in the speech signal. In an experiment on 41 speakers in a Swedish telephone speech database, we compare the use of utterance segmentation produced by automatic and manual methods, and conclude that not much is lost in ASV performance with the automatic method compared to the manual.

[1]  Johan Lindberg,et al.  Text-prompted versus sound-prompted passwords in speaker verification systems , 1997, EUROSPEECH.

[2]  Lawrence G. Bahler,et al.  Speaker verification using randomized phrase prompting , 1991, Digit. Signal Process..

[3]  Don McAllaster,et al.  Speaker verification through large vocabulary continuous speech recognition , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[4]  Aaron E. Rosenberg,et al.  Connected word talker verification using whole word hidden Markov models , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[5]  Jesper Ø. Olsen.  Speaker verification based on phonetic decision making , 1997, EUROSPEECH.

[6]  Gérard Chollet,et al.  Assessment of speaker verification systems , 1995 .

[7]  Frédéric Bimbot,et al.  Speaker verification in the telephone network: research activities in the cave project , 1997, EUROSPEECH.

[8]  Sadaoki Furui,et al.  Concatenated phoneme models for text-variable speaker recognition , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[9]  Håkan Melin.  Gandalf-a Swedish telephone speaker verification database , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.