DocumentCode
339164
Title
A new method for automatic extraction of the voiced/unvoiced feature from Chinese continuous speech using wavelet transform
Author
Hu, Hongtao ; Du Limin
Author_Institution
Inst. of Acoust., Acad. Sinica, China
fYear
1998
fDate
1998
Firstpage
686
Abstract
Based on its physical mechanism and enhancement of the voiced/unvoiced feature, a new method for automatic segmentation of Chinese continuous speech into voiced/unvoiced units is presented, using the wavelet transform. The accuracy and the precision are improved by using the proposed multi-threshold detector
Keywords
feature extraction; speech enhancement; wavelet transforms; Chinese; automatic extraction; automatic segmentation; continuous speech; enhancement; multi-threshold detector; voiced/unvoiced feature; wavelet transform; Acoustic noise; Acoustic waves; Continuous wavelet transforms; Detectors; Displays; Frequency measurement; Friction; Speech analysis; Speech enhancement; Wavelet transforms;
fLanguage
English
Publisher
ieee
Conference_Titel
Signal Processing Proceedings, 1998. ICSP '98. 1998 Fourth International Conference on
Conference_Location
Beijing
Print_ISBN
0-7803-4325-5
Type
conf
DOI
10.1109/ICOSP.1998.770304
Filename
770304
Link To Document