A two-stage procedure for phone based speaker verification

Abstract A two-stage procedure for text prompted speaker verification is presented. In this procedure, speech recognition (segmentation) and speaker verification are carried out separately. In the first stage, Hidden Markov Models are used for identifying phone segments; in the second stage, phoneme dependent Radial Basis Function networks are used for verifying the claimed speaker identity. Phone modelling is important, because different phonemes characterise different aspects of a speaker. It is found here that phone modelling makes it easier to reject impostors, because successful impostors are usually only successful for specific phonemes.

[1]  T. Apostol Multi-variable calculus and linear algebra, with applications to differential equations and probability , 1969 .

[2]  D. F. Morrison,et al.  Multivariate Statistical Methods , 1968 .

[3]  David J. Hand,et al.  Discrimination and Classification , 1982 .

[4]  Sadaoki Furui,et al.  Phoneme-level voice individuality used in speaker recognition , 1994, ICSLP.

[5]  Aaron E. Rosenberg,et al.  Experiments in automatic talker verification using sub-word unit hidden Markov models , 1990, ICSLP.

[6]  Richard J. Mammone,et al.  Application of phonetic weighting to the neural tree network based speaker recognition system , 1995, EUROSPEECH.

[7]  B. Manly Multivariate Statistical Methods : A Primer , 1986 .

[8]  Dafydd Gibbon,et al.  EUROM - a spoken language resource for the EU - the SAM projects , 1995, EUROSPEECH.

[9]  Bruce W. Suter,et al.  The multilayer perceptron as an approximation to a Bayes optimal discriminant function , 1990, IEEE Trans. Neural Networks.

[10]  J.P. Eatock,et al.  A quantitative assessment of the relative speaker discriminating properties of phonemes , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[11]  J. Oglesby,et al.  Radial basis function networks for speaker recognition , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[12]  R. Fisher THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .