α-Gaussian mixture modelling for speaker recognition

Pattern Recognition Letters

Volumn 30, Issue 6, 2009, Pages 589-594

  Wu, Dalei ^a   Li, Ji ^a   Wu, Haiqing ^a  

^a YORK UNIVERSITY   (Canada)

Author keywords

GMM; Gaussian mixture model (GMM); Speaker recognition

Indexed keywords

BRAIN MODELS; COLOR PHOTOGRAPHY; COMMUNICATION CHANNELS (INFORMATION THEORY); MAGNETOSTRICTIVE DEVICES; MIXTURES; OBJECT RECOGNITION; TRELLIS CODES;

COGNITIVE PROCESS; CONVENTIONAL APPROACHES; DATA SETS; GAUSSIAN MIXTURE MODEL (GMM); GAUSSIAN MIXTURES; HUMAN BRAINS; MODEL PARAMETERS; NEW APPROACHES; PSYCHOPHYSICAL EXPERIMENTS; SPEAKER RECOGNITION;

STOCHASTIC MODELS;

EID: 61849130623     PISSN: 01678655     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.patrec.2008.12.013     Document Type: Article

References (16)

1. Amari S. Integration of stochastic models by minimising α-divergence. Neural Comp. 19 (2007) 2780-2796
2. Campbell, J.P., Reynolds, D.A., 1999. Corpora for the evaluation of speaker recognition systems. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing, pp. 829-832.
3. Falthhauser, R., Ruske, G., 2001. Improving speaker recognition performance using phonetically structured Gaussian mixture models. In: Proceedings of the Eurospeech, pp. 751-754.
4. Fisher, W.M., Doddingtion, G.R., Goudie-Marshall, K.M., 1986. The DARPA speech recognition research database: specifications and status. In: Proceedings of DARPA Workshop on Speech Recognition, February 1986, pp. 93-99.
5. Morris, A., Wu, D., Koreman, J., 2005. MLP trained to classify a small number of speakers generates discriminative features for improved speaker recognition. In: Proceedings of the IEEE International Carnahan Conference on Security Technology (ICCST), vol. 11-14, pp. 325-328.
6. Reynolds D.A. Speaker identification and verification using Gaussian mixture speaker models. Speech Commun. 17 (1995) 91-108
7. Reynolds, D.A., 1995c. Large population speaker identification using clean and telephone speech. IEEE Signal Proc. Lett. 2 (3), pp. 46-48.
8. Reynolds, D.A., Zissman, M.A., Quatieri, T.F., Leary, G.C.O., Carlson, B.A., 1995a. The effect of telephone transmission degradations on speaker recognition performance. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing, pp. 329-332.
9. Reynolds, D., Quatieri, T.F., Dunn, R.B., 2000. Speaker verification using adapted Gaussian mixture models. Digit. Signal Process. 10 (1-3), pp. 19-41 (January).
10. Wu, D., 2006. Discriminative Preprocessing of Speech: Towards Improving Biometric Authentication. Ph.D. Thesis, Saarland University, Saarbruecken, Germany, July.
11. Wu, D., Morris, A., Koreman, J., 2005a. MLP internal representation as discriminative features for improved speaker recognition. In: Nonlinear Analyses and Algorithms for Speech Processing Part II (Series: Lecture Notes in Computer Science), pp. 72-78.
12. Wu, D., Morris, A., Koreman, J., 2005b. Discriminative features by MLP preprocessing for robust speaker recognition in noise. In: Proceedings of Electronic Speech Signal Processing, pp. 181-188.
13. Wu, D., Morris, A., Koreman, J., 2005c. MLP internal representation as discriminative features for improved speaker recognition. In: Proceedings of Nonlinear Speech Processing, pp. 25-32.
14. Wu D., Li B.J., and Jiang H. Normalisation and transformation techniques for robust speaker recognition. In: Kordic V. (Ed). Speech Recognition: Techniques, Technology and Applications (2008), Springer Press 1-21
15. Wu, D., 2006. Parameter estimation for α-GMM based on maximum likelihood criterion. Neural Comput. Available from: .
16. Young, S. et al., 2002. HTKbook (V3.2), Cambridge University Engineering Dept.