DocumentCode
2648493
Title
Speaker-independent syllable recognition by a pyramidical neural net
Author
Yang, Shulin ; Ke, Youan ; Wang, Zhong
Author_Institution
Dept. of Electron. Eng., Beijing Inst. of Technol., China
fYear
1991
fDate
18-21 Nov 1991
Firstpage
2189
Abstract
The application of the pyramidical multilayered neural net to speaker-independent recognition of isolated Chinese syllables was investigated. The feature extraction algorithm is described. Experiments involving 90 speakers from 25 provinces of China show that accuracies of 82.7% and 87.1% can be achieved, respectively, for ten isolated digits and seven typical syllables, and an over 75% cross-sex recognition rate can be obtained. The results indicate that this neural net technique can be applied to speaker-independent syllable recognition and that its performance is comparable to that of the hidden Markov model method
Keywords
neural nets; speech recognition; Chinese syllables; feature extraction algorithm; pyramidical neural net; speaker independent speech recognition; Cognition; Data mining; Degradation; Feature extraction; Isolation technology; Multi-layer neural network; Neural networks; Samarium; Speech recognition;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN
0-7803-0227-3
Type
conf
DOI
10.1109/IJCNN.1991.170712
Filename
170712
Link To Document