Reference eigen-environment and speaker weighting for robust speech recognition

Yuan Fu Liao*, Hung Hsiang Fang, Chih Min Yang

*Corresponding author for this work

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

1 Scopus citations

Abstract

In this paper a reference eigen-environment and speaker weighting (RESW) method is proposed for online HMM adaptation. RESW establishes multiple eigen-MLLR subspaces as the set of a priori knowledge according to certain affecting factors, such as noise type, SNR, male and female. It then projects an input test utterance simultaneously into the set of eigen-subspaces and optimally synthesizes out a set of suitable HMMs. The proposed RESW was evaluated on Aurora 2 multi-condition training task. Experimental results showed that average word error rate (WER) of 6.11% was achieved. RESW not only outperformed the multi-condition training baseline (Multi-Con., 13.72%) but also the blind ETSI advanced DSR front-end (ETSI-Adv., 8.65%) and the histogram equalization (HEQ, 8.66%) and the non-blind reference model weighting (RMW, 7.29%) and Eigen-MLLR (6.14%) approaches.

Original languageEnglish
Title of host publicationProceedings - 2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008
Pages77-80
Number of pages4
DOIs
StatePublished - 2008
Event2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008 - Kunming, China
Duration: 16 Dec 200819 Dec 2008

Publication series

NameProceedings - 2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008

Conference

Conference2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008
Country/TerritoryChina
CityKunming
Period16/12/0819/12/08

Keywords

  • Eigen-MLLR
  • Reference model weighting
  • Robust speech recognition

Fingerprint

Dive into the research topics of 'Reference eigen-environment and speaker weighting for robust speech recognition'. Together they form a unique fingerprint.

Cite this