A NEW TIME-FREQUENCY APPROACH FOR UNDERDETERMINED CONVOLUTIVE BLIND SPEECH SEPARATION

被引：0

作者：

Bouafif, Mariem ^{[1
]}

Lachiri, Zied ^{[1
]}

机构：

[1] Natl Engn Sch Tunis ENIT, Signal Image & Informat Technol Lab, Tunis, Tunisia

来源：

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

关键词：

Blind Source Separation; Glottal Closure Instants; Time Delay of Arrival; Weight Function; MIXTURES; MODEL;

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 Time-Frequency approach for recovering sources' contribution to two convolutive mixtures. The separation task is performed on two steps: Each mixture is clustered into Voiced/Unvoiced frames, and then the predominant source in each time frequency bin is identified through a specific weight function which is based on sources' excitation characteristics extraction. We investigate the performance of the proposed approach in the underdetermined context using objective quality measures. Results for separating three and four speech sources in a live recorded mixture show the superiority of the proposed method in rejecting artifacts over existing convolutive separation techniques.

引用

页码：3226 / 3230

页数：5

共 50 条

[1] Underdetermined Convolutive Blind Source Separation via Time-Frequency Masking
Reju, Vaninirappuputhenpurayil Gopalan
Koh, Soo Ngee
Soon, Ing Yann
[J]. IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2010, 18 (01): : 101 - 116
[2] Blind separation of underdetermined convolutive mixtures using their time-frequency representation
Aissa-El-Bey, Abdeldjalil
Abed-Meraim, Karim
Grenier, Yves
[J]. IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2007, 15 (05): : 1540 - 1550
[3] Underdetermined blind separation of convolutive mixtures of speech using time-frequency mask and mixing matrix estimation
Blin, A
Araki, S
Makino, S
[J]. IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2005, E88A (07) : 1693 - 1700
[4] A TIME-FREQUENCY BLIND SEPARATION METHOD FOR UNDERDETERMINED SPEECH MIXTURES
Lv Yao Li Shuangtian(Institute of Acoustics
[J]. Journal of Electronics(China), 2008, (05) : 702 - 708
[5] Time-Frequency Approach to Underdetermined Blind Source Separation
Xie, Shengli
Yang, Liu
Yang, Jun-Mei
Zhou, Guoxu
Xiang, Yong
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2012, 23 (02) : 306 - 316
[6] Blind separation of underdetermined Convolutive speech mixtures by time-frequency masking with the reduction of musical noise of separated signals
Zohrevandi, Mahbanou
Setayeshi, Saeed
Rabiee, Azam
Reshadi, Midia
[J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2021, 80 (08) : 12601 - 12618
[7] Underdetermined blind separation of audio sources from the time-frequency representation of their convolutive mixtures
Aissa-El-Bey, Abdeldjalil
Abed-Meraim, Karim
Grenier, Yves
[J]. 2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PTS 1-3, PROCEEDINGS, 2007, : 153 - 156
[8] A new block based time-frequency approach for underdetermined blind source separation
Luo, Y
Lambotharan, S
Chambers, JA
[J]. 2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL V, PROCEEDINGS: DESIGN AND IMPLEMENTATION OF SIGNAL PROCESSING SYSTEMS INDUSTRY TECHNOLOGY TRACKS MACHINE LEARNING FOR SIGNAL PROCESSING MULTIMEDIA SIGNAL PROCESSING SIGNAL PROCESSING FOR EDUCATION, 2004, : 537 - 540
[9] Underdetermined blind separation of speech signals with delays in different time-frequency domains
Bastari, A
Squartini, S
Piazza, F
[J]. NONLINEAR SPEECH MODELING AND APPLICATIONS, 2005, 3445 : 136 - 163
[10] Underdetermined Blind Source Separation of Anechoic Speech Mixtures in the Time-frequency Domain
Lv Yao
Li Shuangtian
[J]. ICSP: 2008 9TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING, VOLS 1-5, PROCEEDINGS, 2008, : 22 - 25

← 1 2 3 4 5 →