Robustness to telephone handset distortion in speaker recognition by discriminative feature design

Speech Communication

Volumn 31, Issue 2, 2000, Pages 181-192

  Heck, Larry P ^a   Konig, Yochai ^b   Sönmez, M Kemal ^c   Weintraub, Mitch ^a  

^a NUANCE COMMUNICATIONS   (United States)

^b 330 Fell Street   (United States)

^c SRI INTERNATIONAL   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; MULTILAYER NEURAL NETWORKS; SPEECH ANALYSIS; TELEPHONE SETS;

CEPSTRAL MEAN SUBSTRACTION (CMS); HANDSET-DEPENDENT NORMALIZING IMPOSTOR MODELS;

SPEECH RECOGNITION;

EID: 0033746018     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6393(99)00077-1     Document Type: Article

References (26)

1. Baum, E.B., Wilczek, F., 1988. Supervised learning of probability distributions by neural networks. In: D. Anderson, (Ed.), Neural Information Processing Systems. pp. 52-61.
2. Bengio, Y., De Mori, R., Flammia, G., Kompe, R., 1992. Global optmization of a neural network-hidden markov model hybrid. IEEE Trans. Neural Networks 3 (2).
3. Chengalvarayan R., Deng L. HMM-based speech recognition using state-dependent, discriminatively derived transforms on mel-warped DFT features. IEEE Trans. Speech and Audio Process. 5(3):1997;243-256.
4. Euler, S., 1995. Integrated optimization of feature transformation for speech recognition. In: Proceedings European Conf. on Speech Communication and Technology. EUROSPEECH. pp. 109-112.
5. Furui S. Cepstral analysis technique for automatic speaker verification. IEEE Trans. Acoust. Speech Signal Process. ASSP-. 29:1981;254-272.
6. Heck, L.P., Weintraub, M., 1997. Handset dependent background models for robust text-independent speaker recognition. In: Proceedings Internat. Conf. on Acoust. Speech and Signal Process.
7. Hermansky, H., Morgan, N., Bayya, A., Kohn, P., 1991. Compensation for the effect of the communication channel in auditory-like analysis of speech (RASTA-PLP). In: Proceedings European Conf. on Speech Communication and Technology. EUROSPEECH. pp. 1367-1370.
8. Lehr, M., 1996. Scaled stochastic methods for training neural networks, Ph.D. Dissertation, Information Systems Laboratory, Dept. of Electrical Engineering, Stanford University.
9. Liu, F.-H., Stern, R.M., Acero, A., Moreno, P.J., 1994. Environment normalization for robust speech recognition using direct cepstral comparison. In: Proceedings Internat. Conf. on Acoust. Speech Signal Process., Vol. 2, pp. 19-22.
10. Mammone R.J., Shang X., Ramachandran R.P. Robust speaker recognition. IEEE Signal Process. Magazine. 13:1996;58-71.
11. Murthy H.A., Beaufays F., Heck L.P., Weintraub M. Robust text-independent speaker identification over telephone channels. IEEE Trans. Speech and Audio Process. 7:1999;554-568.
12. Neumeyer, L., Weintraub, M., 1994. Probabilistic optimum filtering for robust speech recognition. In: Proceedings Internat. Conf. on Acoust. Speech Signal Process., pp. 417-420.
13. NIST, 1996. Speaker recognition workshop. In: NIST Workshop Notebook, Linthicum Heights, Maryland.
14. NIST, 1997. Speaker recognition workshop. In: NIST Workshop Notebook, Linthicum Heights, Maryland.
15. NIST, 1998. Speaker recognition workshop. In: NIST Workshop Notebook, Linthicum Heights, Maryland.
16. Paliwal, K.K., Bacchiani, M., Sagisaka, Y., 1995. Minimum classification error training algorithm for feature extractor and pattern classifier in speech recognition. In: Proceedings European Conf. on Speech Communication and Technology. EUROSPEECH. pp. 541-544.
17. Przybocki M.A., Martin, A.F., 1998. NIST speaker recognition evaluations. In: LREC, Granada, Spain, pp. 331-335.
18. Quatieri, T.F., Reynolds, D.A., O'Leary, G.C., 1998. Magnitude-only estimation of handset nonlinearity with application to speaker recognition. In: Proceedings Internat. Conf. on Acoust. Speech Signal Process., Vol. 2, pp. 745-748.
19. Rahim, M., Bengio, Y., Lecun, Y., 1997. Discriminative feature and model design for automatic speech recognition. In: Proceedings European Conf. on Speech Communication and Technology. EUROSPEECH. Rhodes, Greece.
20. Reynolds D.A. Speaker identification and verification using Gaussian mixture speaker models. Speech Communication. 17:1995;91-108.
21. Reynolds, D.A., 1997a. Htimit and llhdb: Speech corpora for the study of handset transducer effect. In: Proceedings Internat. Conf. on Acoust. Speech Signal Process., Vol. 2, pp. 1535-1538.
22. Reynolds, D.A., 1997b. Comparison of background normalization methods for text-independent speaker verification. In: Proceedings European Conf. on Speech Communication and Technology. EUROSPEECH.
23. Richard M.D., Lippmann R.P. Neural network classifiers estimate bayesian a posteriori probabilities. Neural Computation. 3(4):1991;461-483.
24. Rumelhart, D.E., Hinton, G.E., Williams, R.J., 1986. Learning internal representations by error propagation. In: Parallel Distributed Processing. MIT Press, Cambridge, pp. 318-364.
25. Stern, R.M., Liu, F.-H., Moreno, P.J., Acero, A., 1994. Signal processing for robust speech recognition. In: Proceedings Internat. Conf. on Spoken Language Process., Vol. 3, pp. 1027-1030.
26. Weintraub, M., 1985. A theory and computational model of auditory monaural sound separation, Ph.D. Dissertation, Stanford University.