Tree-structured model selection and simulated-data adaptation for environmental and speaker robust speech recognition

Thatphithakkul, Nattanun; Kruatrachue, Boontee; Wutiwiwatchai, Chai; Marukatat, Sanparith; Boonpiam, Vataya

doi:10.1109/ISCIT.2007.4392267

Tree-structured model selection and simulated-data adaptation for environmental and speaker robust speech recognition

Author(s)

Thatphithakkul, Nattanun

Kruatrachue, Boontee

Wutiwiwatchai, Chai

Marukatat, Sanparith

Boonpiam, Vataya

Date Issued

December 1, 2007

Type

Conference Paper

DOI

10.1109/ISCIT.2007.4392267

Abstract

This paper proposes the use of tree-structured model selection and simulated-data in maximum likelihood linear regression (MLLR) adaptation for environment and speaker robust speech recognition. The objective of this work is to solve major problems in robust speech recognition system, namely unknown speaker and unknown environmental noise. The proposed solution is composed of two components. The first one is based on a tree-structured model for selecting a speaker-dependent model that best matches to the input speech. The second component uses simulated-data to adapt the selected acoustic model to fit with the unknown noise. The proposed technique can thus alleviate both problems simultaneously. Experimental results show that the proposed system achieves a higher recognition rate than the system using only the input speech in adaptation and the system using a multi-conditioned acoustic model. © 2007 IEEE.

Citation

Iscit 2007 2007 International Symposium on Communications and Information Technologies Proceedings, 1570-1574, 2007