A discriminative neural prediction system for speech recognition

Authors:
A. Mellouk;P. Gallinari
Affiliations:
LRI, CNRS, Université Paris Sud, Orsay cedex, France;LAFORIA, CNRS, Université Paris 6, Paris cedex 05, France
Venue:
ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: plenary, special, audio, underwater acoustics, VLSI, neural networks - Volume I
Year:
1993

Citing 5
Cited 1

Parallel distributed processing: explorations in the microstructure, vol. 2: psychological and biological models

Parallel distributed processing: explorations in the microstructure, vol. 2: psychological and biological models
Large vocabulary speech recognition using neural prediction model

ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
Continuous speech recognition using linked predictive neural networks

ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
Prototype-based discriminative training for various speech units

ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1
A speech recognizer optimally combining learning vector quantization, dynamic programming and multi-layer perceptron

ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1

Predictive connectionist approach to speech recognition

Nonlinear Speech Modeling and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose in this paper a continuous speaker independent speech recognition system based on predictive neural networks for modelizing phonemes, and dynamic time warping for temporal alignment. In this system several modules cooperate together, this allows to incorporate a grammar model and simple correction rules. Our neural networks are trained using a frame discriminative criterion. Tests on TIMIT show 74,5% of correct classification and 68,6% of accuracy which compares well with current systems (The CMU SPHINX System and the Cambridge Recurrent Error Propagation Network).