KALMAN FILTER FOR SPEECH ENHANCEMENT IN COCKTAIL PARTY SCENARIOS USING A CODEBOOK-BASED APPROACH

被引：0

作者：

Kavalekalam, Mathew Shaji ^{[1
]}

Christensen, Mads Graesboll ^{[1
]}

Gran, Fredrik ^{[2
]}

Boldt, Jesper B. ^{[2
]}

机构：

[1] Aalborg Univ, Audio Anal Lab, AD MT, Aalborg, Denmark

[2] GN Resound AS, DK-2750 Ballerup, Denmark

来源：

2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS | 2016年

关键词：

speech enhancement; kalman filter; autoregressive models; SUBSPACE APPROACH; NOISE;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Enhancement of speech in non-stationary background noise is a challenging task, and conventional single channel speech enhancement algorithms have not been able to improve the speech intelligibility in such scenarios. The work proposed in this paper investigates a single channel Kalman filter based speech enhancement algorithm, whose parameters are estimated using a codebook based approach. The results indicate that the enhancement algorithm is able to improve the speech intelligibility and quality according to objective measures. Moreover, we investigate the effects of utilizing a speaker specific trained codebook over a generic speech codebook in relation to the performance of the speech enhancement system.

引用

页码：191 / 195

页数：5

共 23 条

[1]

[Anonymous], 2013, COMPUT REV

[2]

[Anonymous], 2001, PERCEPTUAL EVALUATIO, P862

[3]

[Anonymous], IEEE 2015 AUT SPEECH

[4] Digital noise reduction: Outcomes from laboratory and field studies [J].

Bentler, Ruth ;

Wu, Yu-Hsiang ;

Kettel, Jerrica ;

Hurtig, Richard .

INTERNATIONAL JOURNAL OF AUDIOLOGY, 2008, 47 (08) :447-460

[5] SUPPRESSION OF ACOUSTIC NOISE IN SPEECH USING SPECTRAL SUBTRACTION [J].

BOLL, SF .

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1979, 27 (02) :113-120

[6]

Doclo S., 2008, Handbook on Array Processing and Sensor Networks, P269

[7] STATISTICAL-MODEL-BASED SPEECH ENHANCEMENT SYSTEMS [J].

EPHRAIM, Y .

PROCEEDINGS OF THE IEEE, 1992, 80 (10) :1526-1555

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

EPHRAIM, Y ;

VANTREES, HL .

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

[9] 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

[10] Minimum mean-square error estimation of discrete fourier coefficients with generalized gamma priors [J].

Erkelens, Jan S. ;

Hendriks, Richard C. ;

Heusdens, Richard ;

Jensen, Jesper .

IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2007, 15 (06) :1741-1752

← 1 2 3 →