Neural Networks Applied to Speech Recognition

Hiroaki SAKOE  

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E75-A   No.5   pp.546-551
Publication Date: 1992/05/25
Online ISSN: 
DOI: 
Print ISSN: 0916-8508
Type of Manuscript: INVITED PAPER (Special Section on Nonlinear Dynamics--Adaptive, Learning and Neural Systems--)
Category: 
Keyword: 
neural network,  speech recognition,  dynamic programming,  hidden Markov model,  

Full Text: PDF(493KB)>>
Buy this Article




Summary: 
Applications of neural networks are prevailing in speech recognition research. In this paper, first, suitable role of neural network (mainly back-propagation based multi-layer type) in speech recognition, is discussed. Considering that speech is a long, variable length, structured pattern, a direction, in which neural network is used in cooperation with existing structural analysis frameworks, is recommended. Activities are surveyed, including those intended to cooperatively merge neural networks into dynamic programming based structural analysis framework. It is observed that considerable efforts have been paid to suppress the high nonlinearity of network output. As far as surveyed, no experiment in real field has been reported.