Title :
An off-line working speech recognition system employing a compound neural network and fuzzy logic
Author_Institution :
Dept. of Radio Eng., Beijing Univ. of Posts & Telecommun., China
Abstract :
This paper introduces an off-line working speech recognition hardware system. A new compound structure of neural networks is proposed and fuzzy logic is adopted to implement the system. So the system is able to perform speaker-independent real speech recognition in actual environments where there are heavier noise
Keywords :
backpropagation; digital signal processing chips; fuzzy logic; neural nets; speech recognition; LP-derived cepstrum; TMS320C30 digital signal processor; compound structure; computer-independent hardware system; error backpropagation algorithm; fuzzy logic; hierarchical neural network; neural network training; noise; off-line working speech recognition system; speaker-independent real speech recognition; speech recognition hardware; Fuzzy logic; Neural network hardware; Neural networks; Pattern recognition; Real time systems; Speech processing; Speech recognition; Testing; Vocabulary; Working environment noise;
Conference_Titel :
Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-4428-6
DOI :
10.1109/ICASSP.1998.675467
