Title :
DP matching-based spoken digit recognition using LVQ
Author :
Matsuoka, Toshinobu ; Ishida, Yoshihisa
Author_Institution :
Dept. of Electron. & Commun., Meiji Univ., Kawasaki, Japan
Abstract :
This paper deals with a method of speech recognition using dynamic programming (DP) matching and LVQ techniques. It is well known that learning vector quantization (LVQ) can generate some good reference vectors from many vectors and its algorithm is very simple. On the other hand, the DP matching method has good performance for the recognition of continuous speech. However, in general, this method requires many reference vectors. In this paper, we present a new method of speech recognition using both LVQ clustering and DP matching
Keywords :
dynamic programming; learning (artificial intelligence); neural nets; pattern matching; speech recognition; vector quantisation; clustering; continuous speech; dynamic programming matching; learning vector quantization; speech recognition; spoken digit recognition; Clustering algorithms; Dynamic programming; Electronic mail; Feature extraction; Pattern matching; Speech recognition; Timing; Vector quantization;
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
DOI :
10.1109/ICNN.1995.488196
