DocumentCode :
3239997
Title :
Investigation into a Mel subspace based front-end processing for robust speech recognition
Author :
Selouani, Sid-Ahmed ; O´Shaughnessy, Douglas
Author_Institution :
Moncton Univ., NB, Canada
fYear :
2004
fDate :
18-21 Dec. 2004
Firstpage :
187
Lastpage :
190
Abstract :
This paper addresses the issue of noise reduction applied to robust large-vocabulary continuous-speech recognition (CSR). We investigate strategies based on the subspace filtering that has been proven very effective in the area of speech enhancement. We compare original hybrid techniques that combine the Karhonen-Loeve transform (KLT), multilayer perceptron (MLP) and genetic algorithms (GAs) in order to get less-variant Mel-frequency parameters. The advantages of these methods include that they do not require estimation of either noise or speech spectra. To evaluate the effectiveness of these methods, an extensive set of recognition experiments are carried out in a severe interfering car noise environment for a wide range of SNRs varying from 16 dB to -4 dB using a noisy version of the TIMIT database.
Keywords :
filtering theory; genetic algorithms; multilayer perceptrons; satellite computers; speech enhancement; speech recognition; vocabulary; CSR; GA; KLT; Karhonen-Loeve transform; MLP; Mel-frequency parameter; TIMIT database; front-end processing; genetic algorithm; hybrid technique; large-vocabulary continuous-speech recognition; multilayer perceptron; speech enhancement; speech spectra; subspace filtering; Databases; Filtering; Genetic algorithms; Karhunen-Loeve transforms; Multilayer perceptrons; Noise reduction; Noise robustness; Speech enhancement; Speech recognition; Working environment noise;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing and Information Technology, 2004. Proceedings of the Fourth IEEE International Symposium on
Print_ISBN :
0-7803-8689-2
Type :
conf
DOI :
10.1109/ISSPIT.2004.1433718
Filename :
1433718
Link To Document :
بازگشت