A reference model weighting-based method for robust speech recognition

Yuan Fu Liao, Yh Her Yang, Chi Hui Hsu, Cheng Chang Lee, Jing Teng Zeng

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

In this paper a reference model weighting (RMW) method is proposed for fast hidden Markov model (HMM) adaptation which aims to use only one input test utterance to online estimate the characteristic of the unknown test noisy environment. The idea of RMW is to first collect a set of reference HMMs in the training phase to represent the space of noisy environments, and then synthesize a suitable HMM for the unknown test noisy environment by interpolating the set of reference HMMs. Noisy environment mismatch can hence be efficiently compensated. The proposed method was evaluated on the multi-condition training task of Aurora2 corpus. Experimental results showed that the proposed RMW approach outperformed both the histogram equalization (HEQ) method and the distributed speech recognition (DSR) standard ES 202 212 proposed by European Telecommunications Standards Institute (ETSI).

Original languageEnglish
Title of host publicationInternational Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007
Pages2916-2919
Number of pages4
StatePublished - 2007
Event8th Annual Conference of the International Speech Communication Association, Interspeech 2007 - Antwerp, Belgium
Duration: 27 Aug 200731 Aug 2007

Publication series

NameInternational Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007
Volume4

Conference

Conference8th Annual Conference of the International Speech Communication Association, Interspeech 2007
Country/TerritoryBelgium
CityAntwerp
Period27/08/0731/08/07

Fingerprint

Dive into the research topics of 'A reference model weighting-based method for robust speech recognition'. Together they form a unique fingerprint.

Cite this