Improvement of the speech recognition in noisy environments using a nonparametric regression

Authors:
A. Amrouche;A. Taleb-Ahmed;J. M. Rouvaen;M. C. E. Yagoub
Affiliations:
Faculty of Electronics and Computer Science, USTHB, Bab Ezzouar, Algeria;LAMIH (UMR CNRS 8530), Valenciennes University, Le Mont Houy, France;OAE-IEMN (UMR CNRS 8520), Valenciennes University, Le Mont Houy, France;SITE, University of Ottawa, Ottawa, ON, Canada
Venue:
International Journal of Parallel, Emergent and Distributed Systems
Year:
2009

Citing 9
Cited 0

Review of neural networks for speech recognition

Neural Computation
Probabilistic neural networks and general regression neural networks

Fuzzy logic and neural network handbook
Statistical methods for speech recognition

Statistical methods for speech recognition
Connectionist Speech Recognition: A Hybrid Approach

Connectionist Speech Recognition: A Hybrid Approach
Investigating spoken Arabic digits in speech recognition setting

Information Sciences—Informatics and Computer Science: An International Journal
Arabic word recognition by classifiers and context

Journal of Computer Science and Technology
Neural Networks: A Comprehensive Foundation (3rd Edition)

Neural Networks: A Comprehensive Foundation (3rd Edition)
Connectionist probability estimators in HMM arabic speech recognition using fuzzy logic

MLDM'03 Proceedings of the 3rd international conference on Machine learning and data mining in pattern recognition
Generalized regression neural networks in time-varying environment

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, an efficient speech recognition system based on the general regression neural network (GRNN) has been presented. The GRNN has been previously applied for phoneme identification and isolated word recognition in quiet environment. We propose to extend this method to Arabic spoken word recognition in adverse conditions because noise robustness is one of the most challenging problems in automatic speech recognition (ASR). The proposed system has been tested for Arabic digit recognition at different signal-to-noise ratio (SNR) levels in various noisy conditions, including stationary and nonstationary background noises issued from NOISEX-92 database. The proposed scheme is compared with the similar recognisers based on the multilayer perceptron (MLP), the Elman recurrent neural network (RNN) and the discrete hidden Markov model (HMM). The experimental results show that the use of the neural network approach including nonparametric regression improves the global performance of the speech recogniser in noisy environments.