AN ADAPTIVE TIME-FREQUENCY RESOLUTION APPROACH FOR NON-NEGATIVE MATRIX FACTORIZATION BASED SINGLE CHANNEL SOUND SOURCE SEPARATION

被引：0

作者：

Kirbiz, Serap ^{[1
]}

Smaragdis, Paris ^{[2
]}

机构：

[1] Istanbul Tech Univ, Istanbul, Turkey

[2] Univ Illinois, Champaign, IL USA

来源：

2011 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING | 2011年

关键词：

Non-negative Matrix Factorization; sound source separation; adaptive time-frequency resolution;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

In this paper, we propose an adaptive time-frequency resolution approach for the single channel source separation problem. The aim is to improve the quality and intelligibility of the separated sources by adapting the time-frequency resolution of the analysis window to the characteristic of the signal under consideration. The results evaluated on a large test set show the improvements obtained by the proposed algorithm.

引用

页码：253 / 256

页数：4

共 7 条

[1]

[Anonymous], 2008, SIGN SEP EV CAMP SIS

[2] COMPARING MEASURES OF SPARSITY [J].

Hurley, Niall ;

Rickard, Scott .

2008 IEEE WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING, 2008, :55-60

[3]

Lee DD, 2001, ADV NEUR IN, V13, P556

[4]

Lukin A., 2006, AES 120 CONV PAR, P1

[5]

Painter T, 1997, DSP 97: 1997 13TH INTERNATIONAL CONFERENCE ON DIGITAL SIGNAL PROCESSING PROCEEDINGS, VOLS 1 AND 2, P179, DOI 10.1109/ICDSP.1997.628010

[6]

Schmidt M. N., 2006, P ICA 06 CHARL SC US

[7] Convolutive speech bases and their application to supervised speech separation [J].

Smaragdis, Paris .

IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2007, 15 (01) :1-12

← 1 →