Selecting Good Speech Features for Recognition

Selecting Good Speech Features for Recognition (1996)

by Youngjik Lee , Kyu-Woong Hwang

Citations:

1 - 0 self

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	Selecting Good Speech Features for Recognition	user correction - Legacy Corrections
AUTHOR NAME	Youngjik Lee	user correction - Legacy Corrections
AUTHOR NAME	Kyu-Woong Hwang	user correction - Legacy Corrections
ABSTRACT	This paper describes a method to select a suitable feature for speech recognition using information theoretic measure. Conventional speech recognition systems heuristically choose a portion of frequency components, cepstrum, mel-cepstrum, energy, and their time differences of speech waveforms as their speech features. However, these systems never have good performance if the selected features are not suitable for speech recognition. Since the recognition rate is the only performance measure of speech recognition system, it is hard to judge how suitable the selected feature is. To solve this problem, it is essential to analyze the feature itself, and measure how good the feature itself is. Good speech features should contain all of the classrelated information and as small amount of the class-irrelevant variation as possible. In this paper, we suggest a method to measure the class-related information and the amount of the class-irrelevant variation based on the Shannon's information the...	user correction - Legacy Corrections
YEAR	1996	user correction - Legacy Corrections
CITATIONS	19 found	ParsCit 1.0