论文信息 - Une architecture modulaire pour l'extraction de caractéristiques en reconnaissance de phonèmes

Une architecture modulaire pour l'extraction de caractéristiques en reconnaissance de phonèmes

In this paper, we present an architecture called the Modular Neural Predictive Coding Architecture (MNPC). The Modular NPC is used for Discriminative Feature Extraction (DFE). It provides an architecture based on phonetics knowledge applied to phoneme recognition. The phonemes are extracted from the Darpa-Timit speech database. Comparisons with coding methods (LPC, MFCC, PLP) are presented: they put in obviousness an improvement of the recognition rates.

[1] Mohamed Chetouani,et al. Neural predictive coding for speech discriminant feature extraction: The DFE-NPC , 2002, ESANN.

[2] Antonio M. Peinado,et al. An application of minimum classification error to feature space transformations for speech recognition , 1996, Speech Commun..

[3] Kari Torkkola,et al. On feature extraction by mutual information maximization , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[4] Biing-Hwang Juang,et al. Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.

[5] H. M. Teager,et al. Evidence for Nonlinear Sound Production Mechanisms in the Vocal Tract , 1990 .

[6] Shigeru Katagiri,et al. Handbook of Neural Networks for Speech Processing , 2000 .

[7] Mohamed Chetouani,et al. Maximization of the modelisation error ratio for neural predictive coding , 2003, NOLISP.

[8] Mohamed Chetouani,et al. Modular neural predictive coding for discriminative feature extraction , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[9] Antonio M. Peinado,et al. Discriminative feature weighting for HMM-based continuous speech recognizers , 2002, Speech Commun..