Browse > Article

An Efficient Approach for Noise Robust Speech Recognition by Using the Deterministic Noise Model  

정용주 (계명대학교 컴퓨터.전자공학부)
Abstract
In this paper, we proposed an efficient method that estimates the HMM (Hidden Marke Model) parameters of the noisy speech. In previous methods, noisy speech HMM parameters are usually obtained by analytical methods using the assumed noise statistics. However, as they assume some simplication in the methods, it is difficult to come closely to the real statistics for the noisy speech. Instead of using the simplication, we used some useful statistics from the clean speech HMMs and employed the deterministic noise model. We could find that the new scheme showed improved results with reduced computation cost.
Keywords
Speech recognition; Noisy speech processing; HMM;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 Parallel Model Combination for Speech Recognition in Noise /
[ M.Gales;S.Young ] / Tech. Rep.135
2 Speech Recognition in Noisy Environments /
[ P.Moreno ] / PhD Thesis, Carnegie Mellon Univ.
3 New approaches for domain transformation and parameter combination for improved accuracy in parallel model combinatin (PMC) techniques /
[ J.W.Hung;J.L.Shen;L.S.Lee ] / IEEE Trans. Speech and Audio Processing   DOI   ScienceOn
4 Suppression of acoustic noise in speech using spectral subtraction /
[ S.Boll ] / IEEE Trans. Acoust.,Speech, Signal Processing   DOI
5 Bayesian 적응 방식을 이용한 잡음음성인식에 관한 연구 /
[ 정용주 ] / 한국음향학회지   과학기술학회마을
6 Comparison of parametric representation for monosyllabic word recognition in continuously spoken sentences /
[ Davis,S.B.;Mermelstein,P. ] / IEEE Trans. Acoust., Speech, Signal Processing   DOI
7 A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains /
[ L.E.Baum;G.S.T.Petrie;N.Weiss ] / Ann. Math., Statist.   DOI   ScienceOn