Robust Speech Recognition by Using Compensated Acoustic Scores

Shoei SATO  Kazuo ONOE  Akio KOBAYASHI  Toru IMAI  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E89-D   No.3   pp.915-921
Publication Date: 2006/03/01
Online ISSN: 1745-1361
DOI: 10.1093/ietisy/e89-d.3.915
Print ISSN: 0916-8532
Type of Manuscript: Special Section PAPER (Special Section on Statistical Modeling for Speech Processing)
Category: Speech Recognition
Keyword: 
speech recognition,  noisy environment,  acoustic score,  

Full Text: PDF(307.5KB)>>
Buy this Article




Summary: 
This paper proposes a new compensation method of acoustic scores in the Viterbi search for robust speech recognition. This method introduces noise models to represent a wide variety of noises and realizes robust decoding together with conventional techniques of subtraction and adaptation. This method uses likelihoods of noise models in two ways. One is to calculate a confidence factor for each input frame by comparing likelihoods of speech models and noise models. Then the weight of the acoustic score for a noisy frame is reduced according to the value of the confidence factor for compensation. The other is to use the likelihood of noise model as an alternative that of a silence model when given noisy input. Since a lower confidence factor compresses acoustic scores, the decoder rather relies on language scores and keeps more hypotheses within a fixed search depth for a noisy frame. An experiment using commentary transcriptions of a broadcast sports program (MLB: Major League Baseball) showed that the proposed method obtained a 6.7% relative word error reduction. The method also reduced the relative error rate of key words by 17.9%, and this is expected lead to an improvement metadata extraction accuracy.