HMM-based gain-modeling for enhancement of speech in noise
2007 (English)In: IEEE transactions on speech and audio processing, ISSN 1063-6676, E-ISSN 1558-2353, Vol. 15, no 3, 882-892 p.Article in journal (Refereed) Published
Accurate modeling and estimation of speech and noise gains facilitate good performance of speech. enhancement methods using data-driven prior models. In this paper, we propose a hidden Markov model (HMM)-based speech enhancement method using explicit gain modeling. Through the introduction of stochastic gain variables, energy variation in both speech and noise is explicitly modeled in a unified framework. The speech gain models the energy variations of the speech phones, typically due to differences in pronunciation and/or different vocalizations of individual speakers. The noise gain helps to improve the tracking of the time-varying energy of nonstationary noise. The expectationmaximization (EM) algorithm is used to perform offline estimation of the time-invariant model parameters. The time-varying model'parameters are estimated online using the recursive EM algorithm. The. proposed gain modeling techniques are applied to a novel Bayesian speech estimator, and the performance of the proposed enhancement method is evaluated through objective and subjective tests. The experimental results confirm the advantage of explicit gain modeling, particularly for nonstationary noise sources.
Place, publisher, year, edition, pages
2007. Vol. 15, no 3, 882-892 p.
Gain modeling; Hidden Markov modeling (HMM); Noise suppression; Speech enhancement; Accurate modeling; Bayesian; Data-driven; Energy variations; Expectation-maximization algorithms; Gain modeling; Gain models; Hidden Markov modeling (HMM); Modeling techniques; Noise gains; Noise suppression; Non-stationary noise; Offline; Recursive em; Speech enhancement methods; Subjective tests; Time-invariant models; Time-varying; Time-varying model parameters; Unified frameworks; Polarization; Speech enhancement; Statistical tests; Time varying systems; Hidden Markov models
IdentifiersURN: urn:nbn:se:kth:diva-7235DOI: 10.1109/TASL.2006.885256ISI: 000244318600013ScopusID: 2-s2.0-51449116166OAI: oai:DiVA.org:kth-7235DiVA: diva2:12187
QC 201008252007-05-312007-05-312010-08-25Bibliographically approved