Bayesian feature enhancement using independent vector analysis and reverberation parameter re-estimation for noisy reverberant speech recognition. (November 2017)

• Record Type: Journal Article
• Authors: Cho, Ji-Won; Park, Jong-Hyeon; Chang, Joon-Hyuk; Park, Hyung-Min
• Is Part Of: Computer speech & language. Volume 46(2017)
• Page Start: 496
• Page End: 516
• Publication Date: 2017-11
• Subjects: Robust speech recognition -- Feature enhancement -- Bayesian inference -- Independent vector analysis -- Reverberation -- Hidden Markov model; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2017.01.010
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: A feature enhancement method for noisy reverberant speech recognition is proposed. Clean features are estimated by Bayesian inference in the observation feature model. Both independent vector analysis and reverberation parameter re-estimation are used. Features of speech corrupted by noise and reverberation are efficiently enhanced. Abstract: Because speech recorded by distant microphones in real-world environments is contaminated by both additive noise and reverberation, the automatic speech recognition (ASR) performance is seriously degraded due to the mismatch between the training and testing environments. In the previous studies, some of the authors proposed a Bayesian feature enhancement (BFE) method with re-estimation of reverberation filter parameters for reverberant speech recognition and a BFE method employing independent vector analysis (IVA) to deal with speech corrupted by additive noise. Although both of them accomplish significant improvements in either reverberation- or noise-robust ASR, most of the real-world environments involve both additive noise and reverberation. For robust ASR in the noisy reverberant environments, in this paper, we present a hidden-Markov-model (HMM)-based BFE method using IVA and reverberation parameter re-estimation (RPR) to remove additive and reverberant distortion components in speech acquired by multi-microphones effectively by introducing Bayesian inference in the observation model of input speech features. Experimental results show that the presented method can further reduce the word error rates (WERs) compared with the BFE methods based on conventional noise and/or reverberation models and combinations of the BFE methods for reverberation- or noise-robust ASR.