Corrective training of hidden control neural network

A corrective training algorithm for hidden control neural network (HCNN) is proposed in this paper with application to the isolated spoken Korean digit recognition. The proposed algorithm tries to heuristically minimize the number of recognition errors, which improves the discriminatory power of the...

Full description

Saved in:
Bibliographic Details
Main Authors: KyungMin Na, Soo-Ik Chae, SouGuil Ann
Format: Conference Proceeding
Language:English
Subjects:
Artificial neural networks
Backpropagation algorithms
Electronic mail
Error correction
Hidden Markov models
Maximum likelihood estimation
Neural networks
Predictive models
Speech recognition
Testing
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A corrective training algorithm for hidden control neural network (HCNN) is proposed in this paper with application to the isolated spoken Korean digit recognition. The proposed algorithm tries to heuristically minimize the number of recognition errors, which improves the discriminatory power of the conventional HCNN-based speech recognizers. Experimental results showed 25% reduction for closed test, and 10% reduction for open test in the number of recognition errors.
DOI:10.1109/ICNN.1995.488189