Title :
The Modular Neural Predictive Coding architecture
Author :
Chetouani, M. ; Gas, B. ; Zarader, J.L.
Author_Institution :
Lab. des Instruments et Systemes d´´Ile de France, Paris VI Univ., France
Abstract :
We present a new architecture called the Modular Neural Predictive Coding architecture (Modular NPC). This architecture is used for speech discriminant feature extraction (DFE). We present an application of the modular NPC architecture on phoneme recognition task. The phonemes which are extracted from the Darpa-Timit speech database are: vowels, /b/-/d/-/g/ and /p/-/t/-/k/ phonemes. Comparisons with coding methods (LPC, MFCC, PLP) are presented.
Keywords :
audio databases; feature extraction; neural net architecture; speech recognition; Darpa-Timit speech database; Modular Neural Predictive Coding architecture; coding methods; modular NPC architecture; phoneme recognition; speech discriminant feature extraction; vowels; Feature extraction; Linear predictive coding; Linearity; Mel frequency cepstral coefficient; Optimized production technology; Predictive coding; Predictive models; Speech processing; Speech recognition; Vectors;
Conference_Titel :
Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on
Print_ISBN :
981-04-7524-1
DOI :
10.1109/ICONIP.2002.1202211
