DocumentCode
2949652
Title
Research on ASIC for multi-speaker isolated word recognition
Author
Bing, Xiong ; Yihe, Sun
Author_Institution
Inst. of Microelectron., Tsinghua Univ., Beijing, China
fYear
1996
fDate
21-24 Oct 1996
Firstpage
135
Lastpage
137
Abstract
The ASIC for multi-speaker speech recognition is design in this paper. The LPC-derived cepstral coefficients are chosen as speech features. Templates are trained by K-means clustering algorithm. Two stage recognition system can not only improve recognition accuracy, but also reduce the delay. The first stage of recognition system uses speech spectrum difference (SSD) algorithm. The second stage uses DTW. The whole recognition system is design into ASIC on high level with VHDL and simulated in Powerview
Keywords
application specific integrated circuits; cepstral analysis; linear predictive coding; speech recognition; ASIC; DTW; K-means clustering algorithm; LPC; Powerview simulation; VHDL; cepstral coefficients; high level design; multi-speaker isolated word recognition; speech spectrum difference algorithm; template training; Application specific integrated circuits; Cepstral analysis; Clustering algorithms; Linear predictive coding; Pattern matching; Pattern recognition; Performance evaluation; Speech recognition; Sun; Testing;
fLanguage
English
Publisher
ieee
Conference_Titel
ASIC, 1996., 2nd International Conference on
Conference_Location
Shanghai
Print_ISBN
7-5439-0940-5
Type
conf
DOI
10.1109/ICASIC.1996.562770
Filename
562770
Link To Document