Title :
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
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;
Journal_Title :
Signal Processing Letters, IEEE
DOI :
10.1109/LSP.2013.2283585
