Title :
Word recognition using a neural network and a phonetically based DTW
Author :
Matsuura, Yoshihiro ; Miyazawa, Hideki ; Skinner, Toby E.
Author_Institution :
Meidensha Corp., Tokyo, Japan
Abstract :
The authors have developed a speaker-independent, isolated-word recognition system using a neural network to recognize the underlying sequence of phonemes and a dynamic time warping (DTW) technique to time-align the recognized sequence of phonemes with corresponding lexical sequences of phonemes. A significant feature of this system is the ability to easily change the vocabulary, since the lexical entries are simply derived from their phoneme sequences
Keywords :
neural net architecture; neural nets; speech recognition; dynamic time warping; lexical sequences; neural network; phonemes; speaker-independent isolated-word recognition system; vocabulary; Distortion measurement; Euclidean distance; Feature extraction; Frequency measurement; Neural networks; Parallel processing; Pattern recognition; Speech recognition; Time measurement; Vocabulary;
Conference_Titel :
Neural Networks for Signal Processing [1994] IV. Proceedings of the 1994 IEEE Workshop
Conference_Location :
Ermioni
Print_ISBN :
0-7803-2026-3
DOI :
10.1109/NNSP.1994.366034
