DocumentCode :
2919181
Title :
On the use of hierarchical spectral dynamics in speech recognition
Author :
Furui, Sadaoki
Author_Institution :
NTT Human Interface Lab., Tokyo, Japan
fYear :
1990
fDate :
3-6 Apr 1990
Firstpage :
789
Abstract :
A vector quantization (VQ)-based recognition method which uses feature vector codebooks containing hierarchical spectral dynamics is proposed. This method is highly effective for reducing the number of candidates in word recognition and achieving a high recognition accuracy in /b/,/d/ and /g/ recognition. Since this method does not need time alignment, it has the advantage of a small amount of computation and ease of parallel processing. Experimental results comparing the performances of the multiple-codebook and single-codebook methods indicate that, when the codebook size is small, the multiple-codebook method is better than the single-codebook method. However, if the codebook size is reasonably large, the single-codebook method displays better performance than the multiple-codebook method
Keywords :
encoding; spectral analysis; speech recognition; codebook size; feature vector codebooks; hierarchical spectral dynamics; multiple-codebook method; recognition accuracy; single-codebook method; speech recognition; vector quantization; Concurrent computing; Data preprocessing; Displays; Error analysis; Feature extraction; Humans; Laboratories; Linear predictive coding; Linear regression; Parallel processing; Speech analysis; Speech recognition; Vector quantization; Vocabulary;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on
Conference_Location :
Albuquerque, NM
ISSN :
1520-6149
Type :
conf
DOI :
10.1109/ICASSP.1990.115927
Filename :
115927
Link To Document :
بازگشت