论文信息 - Speaker Recognition Based on the Use of Vocal Tract and Residue Signal LPC Parameters

Speaker Recognition Based on the Use of Vocal Tract and Residue Signal LPC Parameters

The problem of text-independent speaker recognition based on the use of vocal tract and residue signal LPC parameters is investigated. Pseudostationary segments of voiced sounds are used for feature selection. Parameters of the linear prediction model (LPC) of vocal tract and residue sig- nal or LPC derived cepstral parameters are used as features for speaker recognition. Speaker iden- tification is performed by applying nearest neighbour rule to average distance between speakers. Comparison of distributions of intraindividual and interindividual distortions is used for speaker verification. Speaker recognition performance is investigated. Results of experiments demonstrate speaker recognition performance.

Antanas Lipeika | Joana Lipeikiene

[1] Sadaoki Furui,et al. An Overview of Speaker Recognition Technology , 1996 .

[2] Günther Palm,et al. On the use of features from prediction residual signals in speaker identification , 1995, EUROSPEECH.

[3] B.S. Atal,et al. Automatic recognition of speakers from their voices , 1976, Proceedings of the IEEE.

[4] Antanas Lipeika,et al. Speaker identification methods based on pseudostationary segments of voiced sounds , 1996 .

[5] Antanas Lipeika,et al. The use of pseudostationary segments for speaker identification , 1993, EUROSPEECH.

[6] Jr. J.P. Campbell,et al. Speaker recognition: a tutorial , 1997, Proc. IEEE.

[7] Heinz Hügli,et al. Usefulness of the LPC-residue in text-independent speaker verification , 1995, Speech Commun..

[8] Günther Palm,et al. Signal modeling for speaker identification , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.