DocumentCode
1331154
Title
Mandarin speech recognition using segment-based cepstral comparison in noisy conditions
Author
Tung, Shin-Lun ; Juang, Yau-Tarng
Author_Institution
Dept. of Electr. Eng., Nat. Central Univ., Chung-Li, Taiwan
Volume
32
Issue
17
fYear
1996
fDate
8/15/1996 12:00:00 AM
Firstpage
1542
Lastpage
1543
Abstract
A new scheme is proposed that compensates for the effects of noise in speech recognition systems. The new scheme was applied to Mandarin speech recognition. Another scheme, based on interpolation of the compensation vectors of several environments for a particular environment that is not obtained during the training phase, called interpolated SSDCN (ISSDCN), is also presented. Experimental results show that the scheme performs well under different SNR conditions
Keywords
cepstral analysis; compensation; interpolation; random noise; speech recognition; Mandarin speech recognition; SNR conditions; compensation vectors; interpolated SSDCN; interpolation; noise effects compensation; noisy conditions; segment-based cepstral comparison;
fLanguage
English
Journal_Title
Electronics Letters
Publisher
iet
ISSN
0013-5194
Type
jour
DOI
10.1049/el:19961076
Filename
533278
Link To Document