Title: Speech recognition system based on visual features and neural network for persons with speech-impairments

Authors: Zhi-yan Han, Xu Wang, Jian Wang

Addresses: College of Information Science and Engineering, Northeastern University, No. 11, Lane 3, Wenhua Road, Heping District, Shengyang, Liaoning 110004, P.R. China. ' College of Information Science and Engineering, Northeastern University, No. 11, Lane 3, Wenhua Road, Heping District, Shengyang, Liaoning 110004, P.R. China. ' College of Information Science and Engineering, Northeastern University, No. 11, Lane 3, Wenhua Road, Heping District, Shengyang, Liaoning 110004, P.R. China

Abstract: The movements of a talker|s face, nose, mouth and throat are known to convey visual cues and represent several different kinds of information contained in the speech signals that can improve speech recognition rate, especially where there is noise or hearing-impairment. We proposed a new speech recognition method using these visual features and neural network. Genetic algorithm (GA) was first used to replace steepest descent method (SDM) and make a global search of optimal weight in neural network. The improved GA was then used to train the neural network. Six Chinese vowels were taken as the experimental data. Ten handicapped speakers were taken as the subjects. Recognition experiments show that the method is effective and high speed for speech recognition.

Keywords: speech recognition; visual features; genetic algorithms; GAs; neural networks; steepest descent method; SDM; speech impairment; speech impediment; speech signals; Chinese vowels.

DOI: 10.1504/IJMIC.2009.029269

International Journal of Modelling, Identification and Control, 2009 Vol.8 No.3, pp.240 - 247

Published online: 17 Nov 2009 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article