Title :
Environmental Independent ASR Model Adaptation/Compensation by Bayesian Parametric Representation
Author :
Wang, Xuechuan ; Shaughnessy, Douglas O.
Author_Institution :
Inst. Nat. de la Recherche Scientifique, Montreal, Que.
fDate :
5/1/2007 12:00:00 AM
Abstract :
The mismatch between system training and operating conditions can seriously deteriorate the performance of automatic speech recognition (ASR) systems. Various techniques have been proposed to solve this problem in a specified speech environment. Employment of these techniques often involves modification on the ASR system structure. In this paper, we propose an environment-independent (EI) ASR model parameter adaptation approach based on Bayesian parametric representation (BPR), which is able to adapt ASR models to new environments without changing the structure of an ASR system. The parameter set of BPR is optimized by a maximum joint likelihood criterion which is consistent with that of the hidden Markov model (HMM)-based ASR model through an independent expectation-maximization (EM) procedure. Variations of the proposed approach are investigated in the experiments designed in two different speech environments: one is the noisy environment provided by the AURORA 2 database, and the other is the network environment provided by the NTIMIT database. Performances of the proposed EI ASR model compensation approach are compared to those of the cepstral mean normalization (CMN) approach, which is one of the standard techniques for additive noise compensation. The experimental results show that performances of ASR models in different speech environments are significantly improved after being adapted by the proposed BPR model compensation approach
Keywords :
Bayes methods; expectation-maximisation algorithm; hidden Markov models; speech recognition; Bayesian parametric representation; HMM; additive noise compensation; automatic speech recognition; cepstral mean normalization; environmental independent ASR model; hidden Markov model; independent expectation-maximization procedure; maximum joint likelihood criterion; Adaptation model; Additive noise; Automatic speech recognition; Bayesian methods; Business process re-engineering; Cepstral analysis; Databases; Employment; Hidden Markov models; Working environment noise; Automatic speech recognition (ASR); Bayesian parametric representation (BPR); environment compensation; model adaptation;
Journal_Title :
Audio, Speech, and Language Processing, IEEE Transactions on
DOI :
10.1109/TASL.2007.894523