GMM based Bayesian approach to speech enhancement in signal transform domain

被引：24

作者：

Kundu, Achintya ^{[1
]}

Chatterjee, Saikat ^{[1
]}

Murthy, A. Sreenivasa ^{[1
]}

Sreenivas, T. V. ^{[1
]}

机构：

[1] Indian Inst Sci, Dept Elect Commun Engn, Bangalore 560012, Karnataka, India

来源：

2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12 | 2008年

关键词：

MMSE estimation; GMM; Gaussian noise;

D O I：

10.1109/ICASSP.2008.4518754

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Considering a general linear model of signal degradation, by modeling the probability density function (PDF) of the clean signal using a Gaussian mixture model (GMM) and additive noise by a Gaussian PDF, we derive the minimum mean square error (MMSE) estimator. The derived MMSE estimator is non-linear and the linear MMSE estimator is shown to be a special case. For speech signal corrupted by independent additive noise, by modeling the joint PDF of time-domain speech samples of a speech frame using a GMM, we propose a speech enhancement method based on the derived MMSE estimator. We also show that the same estimator can be used for transform-domain speech enhancement.

引用

页码：4893 / 4896

页数：4

共 12 条

[1]

Breithaupt C, 2003, 2003 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS, P896

[2] Estimating cepstrum of speech under the presence of noise using a joint prior of static and dynamic features [J].

Deng, L ;

Droppo, J ;

Acero, A .

IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2004, 12 (03) :218-233

[3] A BAYESIAN-ESTIMATION APPROACH FOR SPEECH ENHANCEMENT USING HIDDEN MARKOV-MODELS [J].

EPHRAIM, Y .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1992, 40 (04) :725-735

[4] A SIGNAL SUBSPACE APPROACH FOR SPEECH ENHANCEMENT [J].

EPHRAIM, Y ;

VANTREES, HL .

IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1995, 3 (04) :251-266

[5] SPEECH ENHANCEMENT USING A MINIMUM MEAN-SQUARE ERROR SHORT-TIME SPECTRAL AMPLITUDE ESTIMATOR [J].

EPHRAIM, Y ;

MALAH, D .

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1984, 32 (06) :1109-1121

[6] Speech enhancement employing Laplacian-Gaussian mixture [J].

Gazor, S ;

Zhang, W .

IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2005, 13 (05) :896-904

[7] Speech probability distribution [J].

Gazor, S ;

Zhang, W .

IEEE SIGNAL PROCESSING LETTERS, 2003, 10 (07) :204-207

[8] A generalized subspace approach for enhancing speech corrupted by colored noise [J].

Hu, Y ;

Loizou, PC .

IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2003, 11 (04) :334-341

[9]

KAY SM, 1993, FUNDAMENTALS STAT SI, V2, P364

[10]

Loizou P. C., 2007, SPEECH ENHANCEMENT T

← 1 2 →