SPEECH-GUIDED SOURCE SEPARATION USING A PITCH-ADAPTIVE GUIDE SIGNAL MODEL

被引：0

作者：

Hennequin, Romain ^{[1
]}

Burred, Juan Jose ^{[1
]}

Maller, Simon ^{[1
]}

Leveau, Pierre ^{[1
]}

机构：

[1] Audionamix, F-75010 Paris, France

来源：

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

关键词：

Audio source separation; non-negative matrix factorization; informed source separation;

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 present a new method to perform underdetermined audio source separation using a spoken or sung reference signal to inform the separation process. This method explicitly models possible differences between the spoken reference and the target signal, such as pitch differences and time lag. We show that the proposed algorithm outperforms state-of-the art methods.

引用

页数：5

共 16 条

[1]

[Anonymous], IEEE INT C AC SPEECH

[2]

Durrieu Jean-Louis, 2012, Latent Variable Analysis and Signal Separation. Proceedings 10th International Conference, LVA/ICA 2012, P438, DOI 10.1007/978-3-642-28551-6_54

[3] AN ITERATIVE APPROACH TO MONAURAL MUSICAL MIXTURE DE-SOLOING [J].

Durrieu, Jean-Louis ;

Richard, Gael ;

David, Bertrand .

2009 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1- 8, PROCEEDINGS, 2009, :105-108

[4] Nonnegative Matrix Factorization with the Itakura-Saito Divergence: With Application to Music Analysis [J].

Fevotte, Cedric ;

Bertin, Nancy ;

Durrieu, Jean-Louis .

NEURAL COMPUTATION, 2009, 21 (03) :793-830

[5]

FitzGerald D, 2012, EUR SIGNAL PR CONF, P2412

[6]

Ganseman Joachim, 2010, INT SOC MUS INF RETR

[7] TEXT-INFORMED AUDIO SOURCE SEPARATION USING NONNEGATIVE MATRIX PARTIAL CO-FACTORIZATION [J].

Le Magoarou, Luc ;

Ozerov, Alexey ;

Duong, Ngoc Q. K. .

2013 IEEE INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP), 2013,

[8]

Leveau P, 2011, 2011 IEEE WORKSHOP ON APPLICATIONS OF SIGNAL PROCESSING TO AUDIO AND ACOUSTICS (WASPAA), P165, DOI 10.1109/ASPAA.2011.6082287

[9] A Watermarking-Based Method for Informed Source Separation of Audio Signals With a Single Sensor [J].

Parvaix, Mathieu ;

Girin, Laurent ;

Brossier, Jean-Marc .

IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2010, 18 (06) :1464-1475

[10]

Pedone Agnes, 2011, ANN C INT SPEECH COM

← 1 2 →