Skip to content

Detail of publication

Citation

Prcín, M. and Müller, L. : Heuristic and statistical methods for speech/non-speech detector design . Lecture Notes in Artificial Intelligence, 2448, p. 309-316, 2002.

Abstract

The speech/non-speech (S/NS) detection is very important for automatic speech recognition (ASR), especially in the case of isolated words or commands recognition This paper proposes a novel approach that finds robust features for better endpoint detection in a noisy environment In the proposed method, we make use of advantages of the both approaches (i.e. to try to find the best set of heuristic features and apply a statistical induction method)

Detail of publication

Title: Heuristic and statistical methods for speech/non-speech detector design
Author: Prcín, M. ; Müller, L.
Language: English
Date of publication: 1 Jan 2002
Year: 2002
Type of publication: Papers in journals
Title of journal or book: Lecture Notes in Artificial Intelligence
Series: 2448
Page: 309 - 316
ISBN: 0302-9743
/ /

Keywords

speech recognition, heuristic methods, statistical methods

BibTeX

@ARTICLE{PrcinM_2002_Heuristicand,
 author = {Prc\'{i}n, M. and M\"{u}ller, L.},
 title = {Heuristic and statistical methods for speech/non-speech detector design},
 year = {2002},
 journal = {Lecture Notes in Artificial Intelligence},
 pages = {309-316},
 series = {2448},
 ISBN = {0302-9743},
 url = {http://www.kky.zcu.cz/en/publications/PrcinM_2002_Heuristicand},
}