Title :
Modular neural predictive coding for discriminative feature extraction
Author :
Chetouani, M. ; Gas, B. ; Zarader, J.L.
Author_Institution :
Lab. des Instruments et Systemes d´´Ile-De-France, Universite Paris VI, France
Abstract :
We present an architecture called the modular neural predictive coding architecture (Modular NPC). 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.
Keywords :
data compression; feature extraction; neural nets; prediction theory; speech coding; speech recognition; Darpa-Timit speech database; LPC; MFCC; PLP; discriminative feature extraction; modular neural predictive coding; phoneme recognition; phonetics knowledge; recognition rate; Cepstral analysis; Context modeling; Feature extraction; Instruments; Linear predictive coding; Mel frequency cepstral coefficient; Predictive coding; Predictive models; Spatial databases; Speech;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on
Print_ISBN :
0-7803-7663-3
DOI :
10.1109/ICASSP.2003.1202287
