scispace - formally typeset
Proceedings ArticleDOI

A three-hierarchy neural network structure and its application to the speaker-independent speech recognition of Chinese words

Zhou Liqing, +1 more
- Vol. 3, pp 1278-1281
TLDR
A three-hierarchical structure of neural networks is proposed and applied to the speaker-independent speech recognition for Chinese digits 0-9 and shows good performance on persons under test from different provinces speaking the same Chinese words in a normal environment.
Abstract: 
A three-hierarchical structure of neural networks is proposed in this paper. The structure is applied to the speaker-independent speech recognition for Chinese digits 0-9. The experimental result shows that the system gave good performance on persons under test from different provinces speaking the same Chinese words in a normal environment.

read more

References
More filters
Book ChapterDOI

Learning internal representations by error propagation

David E. Rumelhart, +2 more
TL;DR: This chapter contains sections titled: The Problem, The Generalized Delta Rule, Simulation Results, Some Further Generalizations, Conclusion.
Book

Learning internal representations by error propagation

David E. Rumelhart, +2 more
TL;DR: In this paper, the problem of the generalized delta rule is discussed and the Generalized Delta Rule is applied to the simulation results of simulation results in terms of the generalized delta rule.
Book

Digital Processing of Speech Signals

Lawrence R. Rabiner, +1 more
TL;DR: This paper presents a meta-modelling framework for digital Speech Processing for Man-Machine Communication by Voice that automates the very labor-intensive and therefore time-heavy and expensive process of encoding and decoding speech.
Journal ArticleDOI

Signal modeling techniques in speech recognition

Joseph Picone
TL;DR: A tutorial on signal processing in state-of-the-art speech recognition systems is presented, reviewing those techniques most commonly used, and three important trends that have developed in the last five years in speech recognition are examined.
Proceedings ArticleDOI

Design of hierarchical perceptron structures and their application to the task of isolated-word recognition

Kammerer, +1 more
TL;DR: Several design strategies for feedforward networks are examined within the scope of pattern classification and a hierarchical structure with pairwise training of two-class models is superior to a single uniform network for speaker-independent word recognition.