Issues in frequency domain blind source separation - A critical revisit

被引：0

作者：

Robledo-Amuncio, E ^{[1
]}

Juang, BH ^{[1
]}

机构：

[1] Georgia Inst Technol, Ctr Signal & Image Proc, Atlanta, GA 30332 USA

来源：

2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING | 2005年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

One of the most important problems in frequency domain blind source separation (FDBSS) is the inconsistency across frequency in the permutation of the source estimates. According to previous studies, this problem can be reduced significantly by constraining the length of the unmixing filters. This improvement has been attributed to the smoothening of the unmixing frequency response. In this paper we study the effect of modifying these length constraints taking into account the circularity of the IDFT, and we show that the smoothening of the unmixing frequency response alone can not account for the improvements in performance.

引用

页码：281 / 284

页数：4

共 50 条

[1] Blind source separation in frequency domain
Zhou, Y
Xu, BL
SIGNAL PROCESSING, 2003, 83 (09) : 2037 - 2046
[2] A novel approach to blind source separation in the frequency domain
Departamento de Electrónica, Universidade da Coruña, Campus de Elviña S/n, 15.071. A Coruña, Spain
Advances in Neural Networks and Applications, 2001, : 315 - 320
[3] Blind source separation of many signals in the frequency domain
Mukai, Ryo
Sawada, Hiroshi
Araki, Shoko
Makino, Shoji
2006 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-13, 2006, : 5827 - 5830
[4] Evaluation of separation and dereverberation performance in frequency domain blind source separation
Mukai, Ryo
Araki, Shoko
Sawada, Hiroshi
Makino, Shoji
Acoust. Sci. Technol., 1600, 2 (119-126):
[5] The Relationship between Frequency Domain Blind Source Separation and Frequency Domain Adaptive Beamformer
Qian Sichong
Xiang Yang
MECHANICAL DESIGN AND POWER ENGINEERING, PTS 1 AND 2, 2014, 490-491 : 654 - 662
[6] Equivalence between frequency domain blind source separation and frequency domain adaptive beamforming
Araki, S
Hinamoto, Y
Makino, S
Nishikawa, T
Mukai, R
Saruwatari, H
2002 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-IV, PROCEEDINGS, 2002, : 1785 - 1788
[7] A PARTITIONED FREQUENCY DOMAIN ALGORITHM FOR CONVOLUTIVE BLIND SOURCE SEPARATION
Scarpiniti, Michele
Picaro, Andrea
Parisi, Raffaele
Uncini, Aurelio
2009 IEEE INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING, 2009, : 411 - 416
[8] Frequency domain blind source separation for many speech signals
Mukai, R
Sawada, H
Araki, S
Makino, S
INDEPENDENT COMPONENT ANALYSIS AND BLIND SIGNAL SEPARATION, 2004, 3195 : 461 - 469
[9] Performance evaluation for frequency domain blind source separation algorithms
Na, Y. (08112069@bjtu.edu.cn), 1600, Binary Information Press, P.O. Box 162, Bethel, CT 06801-0162, United States (09):
[10] Blind source separation of convolutive mixtures of speech in frequency domain
Makino, S
Sawada, H
Mukai, R
Araki, S
IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2005, E88A (07) : 1640 - 1655

← 1 2 3 4 5 →