An Efficient HMM-Based Feature Enhancement Method With Filter Estimation for Reverberant Speech Recognition

Author

Ji-Won Cho ; Hyung-Min Park

Author_Institution

Dept. of Electron. Eng., Sogang Univ., Seoul, South Korea

Volume

20

Issue

12

fYear

2013

fDate

Dec. 2013

Firstpage

1199

Lastpage

1202

Abstract

This letter presents an efficient feature enhancement method for reverberant speech recognition that derives a minimum mean square error estimate of clean logarithmic mel-frequency power spectral coefficients (LMPSCs) based on a hidden-Markov-model(HMM) prior. Although an observation model of the reverberant LMPSCs can be simply formulated by coarse modeling of the room impulse response (RIR) , the presented method estimates not only the clean LMPSCs but also the RIR to reflect detailed reverberation. The experimental results indicate that the described method can further reduce relative word error rate (WER) by 18.09% on average compared to a method based on RIR coarse modeling.

Keywords

hidden Markov models; least mean squares methods; reverberation; speech recognition; LMPSC; RIR; WER; coarse modeling; efficient HMM based feature enhancement method; filter estimation; hidden Markov model; logarithmic mel-frequency power spectral coefficients; mean square error estimation; reverberant speech recognition; room impulse response; word error rate; Bayes methods; Hidden Markov models; Reverberation; Robustness; Speech enhancement; Speech recognition; Bayesian inference; feature enhancement; reverberant speech recognition; room impulse response;

fLanguage

English

Journal_Title

Signal Processing Letters, IEEE

Publisher

ieee

ISSN

1070-9908

Type

jour

DOI

10.1109/LSP.2013.2283585

Filename

6612661