DocumentCode
437056
Title
Robust speech recognition based on neighborhood space
Author
Yan, Binfeng ; Zhu, Xiaoyan
Author_Institution
State Key Laboratory of Intelligent Technol. & Syst., Tsinghua Univ., Beijing, China
Volume
1
fYear
2004
fDate
31 Aug.-4 Sept. 2004
Firstpage
613
Abstract
In this paper, we present an approach to robust speech recognition based on neighborhood space. To achieve performance robustness under mismatch between training and testing conditions, we propose to use neighborhood space of each underlying model to produce Bayesian predictive density as observation probability density. Experimental results show that the proposed method improves the performance robustness.
Keywords
Bayes methods; probability; speech recognition; Bayesian predictive density; neighborhood space; observation probability density; robust speech recognition; Acoustic noise; Acoustic testing; Automatic speech recognition; Bayesian methods; Hidden Markov models; Laboratories; Predictive models; Robustness; Space technology; Speech recognition;
fLanguage
English
Publisher
ieee
Conference_Titel
Signal Processing, 2004. Proceedings. ICSP '04. 2004 7th International Conference on
Print_ISBN
0-7803-8406-7
Type
conf
DOI
10.1109/ICOSP.2004.1452738
Filename
1452738
Link To Document