A New Approach To Speech Coding: the Neural Predictive Coding

Journal of Advanced Computational Intelligence and Intelligent Informatics

Volumn 4, Issue 1, 2000, Pages 120-127

  Gas, Bruno ^a   Zarader, Jean Luc ^a   Chavy, Cyril ^a  

^a SORBONNE UNIVERSITÉ   (France)

Author keywords

Discriminant feature extraction (DFE); Neural networks; Non linear predictive coding; Phonemes recognition; Speech signal coding

Indexed keywords

AUDIO SIGNAL PROCESSING; CODES (SYMBOLS); NETWORK CODING; SPEECH COMMUNICATION; SPEECH PROCESSING; SPEECH RECOGNITION;

DISCRIMINANT FEATURE EXTRACTION; LINEAR PREDICTIVE CODING; NEURAL-NETWORKS; NON LINEAR; NON LINEAR PREDICTIVE CODING; PHONEMES RECOGNITION; SIGNAL CODING; SPEECH SIGNAL CODING; SPEECH SIGNALS;

DISCRIMINANT ANALYSIS;

EID: 0005855325     PISSN: 13430130     EISSN: 18838014     Source Type: Journal    
DOI: 10.20965/jaciii.2000.p0120     Document Type: Article

References (27)

1. A. Biem and S. Katagiri. Feature extraction based on minimum classification error/generalized probabilistic descent method. In Proceedings of Internationa! Conference on Signal and Speech Processing, volume 2, pages 275-278, 1993.
2. A. Biem and S, Katagiri. Filter bank design based on discriminative feature extraction. In Proceedings of international Conference on Signal and Speech Processing, volume 1, pages 485-488, 1994.
3. S. B. Davis and P. Melmerstein. Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Transactions on Acoustic, Speech and Signal Processing, 28(4):357-376, 1980.
4. A. de la Torre, A, M, Peinado, A. J. Rubio, V. E. Sanchez, and J. E. Diaz. An application of minimum classification error to feature space transformations for speech recognition. Speech Communication, 20:273-290, 1996.
5. T. Kawahara and S. Doshita, Phoneme recognition by combining discriminant analysis and hmm. In Proceedings of International Conference on Signal and Speech Processing, volume 1, pages 557-560, 1991
6. T. Kawahara, T Qgawa» S. Kitazawa, and S. Dos hit a. Phoneme recognition by combining hayesian linear discriminations of selected pairs of classes. In Proceedings of international Conference on Signal and Speech Processings page 78, 1990
7. University of Pennsylvania Linguistic Data-Consortium. Darpatimit: a multi speakers data base
8. r Marcos, O. Netrand, L. Personnaz, Rewssel R;tgo T. D. Urb;mi, und C. Vignat. Adaptive training of feedback neural networks for non linear filtering- Neural Networks for signal processing, 2:550-559, 1992
9. K. S. Fu. Syntactic Methods in Pattern Recognition. Academic Press, 1974.
10. T 1987.
11. K. Hornik. Multilayer feedforward networks are universal approximators. Neural Networks, 2:359-366, 1989.
12. F. Itakura. Minimum prediction residual principle applied to speech recognition. IEEE Transactions on Acoustic, Speech and Signal Processing. 23:67-72, 1975.
13. H. H. Juang and S. Ratagiri. Discriminative Learning for minimum error classification. IEEE Transactions on Signal Processing, 40(12): 3043-3054, december 1992.
14. T Kohonen, The 'neural' phonetic typewriter. IEEE Computer, 21(3), 1988
15. T. Kohonen and al. Phonotopic maps insightful representation of phonological features for speech recognition. In Proceedings ofInternational Conference on Pattern Recognition, volume 7, 1984.
16. K. J, Lang, A. H. Waibel, and G.E. H in ton. A time-delay neural network architecture for isolated word recognition, Neural Networks, 3:23-43. 1990.
17. A. Lapedes and R Farber. Nonlinear signal processing using neural networks: Prediction;ind system modelling. Internal Report, Los Alamos National Laboratory. July 1987.
18. Y Lecun. ModOles eonnexionnistes de Vapprentisssages. PhD thesis, Pans XL 1987
19. S. B. Lcvinson. Structural methods in automatic speech recognition. Procedings of the IEEE. 73(11): 1625-1650, July 1987.
20. J. D, Market. Linear prediction of speech. Springer Verlag, Berlin. Heidelberg, New York, 1976.
21. D. E. Rumelhart, G, E. Hmton, and R.J. Williams. Learning representations by back-propagating errors. Nature, 323:533-536, 1986
22. T March 1989.
23. B. Widrow. 30 years of adaptative neural networks: Pcrccptron, madalinc and backpropagation. Proc. of the IEEE, 78:1415-1442, 1990.
24. S, A, Zahorian, D. Qian, and A.J. JagharghL Acoustic-phonetic transformations for improved speaker-independent isolated word recognition. In Preeeedings of International Conference on Signal and Speech Processing, volume 1, pages 561-564, 1991.
25. J. Thysscn, H. Nielsen, and S, D, Hansen. Non-linear short-term prediction in speech coding' In Proceedings of International Conference on Signal and Speech Processing, volume 1, pages 185-188, 1994.
26. N. Tishby. A dynamical system approach to speech processing. In Proceedings of International Conference on Signal and Speech Processingi volume 1, pages 365-368, 1990
27. B. Townshend. Non linear prediction os speech. In Proceedings of International Conference on Signal and Speech Processing, volume 1, pages 425-428, 1991.