Title :
Multi-model approach for noisy speech recognition
Author :
Guan, Cun-tai ; Leung, Shu-hung ; Wing-Hong Lan
Author_Institution :
Dept. of Electron. Eng., City Univ. of Hong Kong, Hong Kong
fDate :
1/8/1998 12:00:00 AM
Abstract :
A multi-model approach for noisy speech recognition is proposed. This approach comprised an SVD-based preprocessing front-end and a multi-model HMM recognition structure. It can provide a high recognition rate over a large range of SNRs for speech recognition in wide-band additive noise
Keywords :
hidden Markov models; random noise; singular value decomposition; speech recognition; HMM recognition structure; SNRs; SVD-based preprocessing front-end; multi-model approach; noisy speech recognition; recognition rate; wideband additive noise;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19980042
