ROBUST MMSE FILTERING FOR SINGLE-MICROPHONE SPEECH ENHANCEMENT

被引：0

作者：

Enzner, Gerald ^{[1
]}

Thuene, Philipp ^{[1
]}

机构：

[1] Ruhr Univ Bochum, Adapt Syst Lab, D-44780 Bochum, Germany

来源：

2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2017年

关键词：

optimum filtering; speech enhancement; SPECTRAL AMPLITUDE ESTIMATOR; SQUARE ERROR ESTIMATION; NOISE-REDUCTION; MUSICAL NOISE; SUPPRESSION; SUBTRACTION; EPHRAIM; PRIORS;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

MMSE filtering of signals contaminated with additive noise is addressed with explicit uncertainty of the second-order target signal statistics. The unfortunate lack of stationarity of speech, and hence the phenomenon of musical noise in speech enhancement, is an ideal problem for the proposed approach. Specifically, we complement the established short-time power-spectral subtraction for speech power estimation with a prior of the momentary speech-power level. The MMSE estimator for Gaussian speech amplitudes is then derived under these circumstances. The potential for the enhancement of noisy speech is briefly demonstrated by SNR and PESQ analysis.

引用

页码：4009 / 4013

页数：5

共 50 条

[21] Bayesian MMSE Filtering of Noisy Speech by SNR Marginalization With Global PSD Priors [J].

Enzner, Gerald ;

Thuene, Philipp .

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2018, 26 (12) :2289-2304

[22] A brief overview of speech enhancement with linear filtering [J].

Benesty, Jacob ;

Christensen, Mads Graesboll ;

Jensen, Jesper Rindom ;

Chen, Jingdong .

EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING, 2014,

[23] A SPEECH ENHANCEMENT ALGORITHM BY ITERATING SINGLE- AND MULTI-MICROPHONE PROCESSING AND ITS APPLICATION TO ROBUST ASR [J].

Zhang, Xueliang ;

Wang, Zhong-Qiu ;

Wang, DeLiang .

2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, :276-280

[24] Speech detection and enhancement using single microphone for distant speech applications in reverberant environments [J].

Kothapally, Vinay ;

Hansen, John H. L. .

18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION, 2017, :1948-1952

[25] Noise Correlation Matrix Estimation for Multi-Microphone Speech Enhancement [J].

Hendriks, Richard C. ;

Gerkmann, Timo .

IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2012, 20 (01) :223-233

[26] MMSE Log-Spectral Amplitude Estimation for Single Channel Speech Enhancement under Speech Presence Uncertainty by Weibull Speech Priors [J].

Bahrami, Mojtaba ;

Seyedin, Sanaz .

26TH IRANIAN CONFERENCE ON ELECTRICAL ENGINEERING (ICEE 2018), 2018, :749-754

[27] Robust speech processing using local adaptive non-linear filtering [J].

Diaz-Ramirez, Victor H. ;

Kober, Vitaly .

IET SIGNAL PROCESSING, 2013, 7 (05) :345-359

[28] Speech enhancement based on harmonic estimation combined with MMSE to improve speech intelligibility for cochlear implant recipients [J].

Wang, Dongmei ;

Hansen, John H. L. .

18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION, 2017, :186-190

[29] SINGLE-MICROPHONE LATE-REVERBERATION SUPPRESSION IN NOISY SPEECH BY EXPLOITING LONG-TERM CORRELATION IN THE DFT DOMAIN [J].

Erkelens, Jan S. ;

Heusdens, Richard .

2009 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1- 8, PROCEEDINGS, 2009, :3997-4000

[30] MMSE-OPTIMAL ENHANCEMENT OF COMPLEX SPEECH COEFFICIENTS WITH UNCERTAIN PRIOR KNOWLEDGE OF THE CLEAN SPEECH PHASE [J].

Gerkmann, Timo .

2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2014,

← 1 2 3 4 5 →