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

[31] A Time–Frequency Domain Blind Source Separation Method for Underdetermined Instantaneous Mixtures [J].

Tianliang Peng ;

Yang Chen ;

Zengli Liu .

Circuits, Systems, and Signal Processing, 2015, 34 :3883-3895

[32] A New Initialization Method for Frequency-Domain Blind Source Separation Algorithms [J].

Clark, Felipe S. P. ;

Petraglia, Mariane R. ;

Haddad, Diego B. .

IEEE SIGNAL PROCESSING LETTERS, 2011, 18 (06) :343-346

[33] Frequency domain blind source separation exploiting higher-order dependencies [J].

Kim, Taesu ;

Attias, Hagai ;

Lee, Soo-Young ;

Lee, Te-Won .

2006 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-13, 2006, :5535-5538

[34] A novel hybrid approach to the permutation problem of frequency domain blind source separation [J].

Wang, WW ;

Chambers, JA ;

Sanei, S .

INDEPENDENT COMPONENT ANALYSIS AND BLIND SIGNAL SEPARATION, 2004, 3195 :532-539

[35] Fundamental limitation of frequency domain Blind Source Separation for convolutive mixture of speech [J].

Shoko, A ;

Shoji, M ;

Nishikawa, T ;

Saruwatari, H .

2001 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-VI, PROCEEDINGS: VOL I: SPEECH PROCESSING 1; VOL II: SPEECH PROCESSING 2 IND TECHNOL TRACK DESIGN & IMPLEMENTATION OF SIGNAL PROCESSING SYSTEMS NEURALNETWORKS FOR SIGNAL PROCESSING; VOL III: IMAGE & MULTIDIMENSIONAL SIGNAL PROCESSING MULTIMEDIA SIGNAL PROCESSING, 2001, :2737-2740

[36] Improved Method for Solving Permutation Problem of Frequency Domain Blind Source Separation [J].

Wang Weihua ;

Huang Fenggang .

2008 6TH IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL INFORMATICS, VOLS 1-3, 2008, :670-673

[37] Underdetermined blind separation of delayed sound source in the time-frequency domain [J].

Xia, X. (xiaxxy@163.com), 1600, Sichuan University (46)

[38] Suppressing directional interference combining frequency domain blind source separation with beamforming [J].

Kang, Chunyu, 1600, Science Press (39)

[39] Near-field frequency domain blind source separation for convolutive mixtures [J].

Mukai, R ;

Sawada, H ;

Araki, S ;

Makino, S .

2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL IV, PROCEEDINGS: AUDIO AND ELECTROACOUSTICS SIGNAL PROCESSING FOR COMMUNICATIONS, 2004, :49-52

[40] INCREMENTAL METHOD OF PERMUTATION ALIGNMENT FOR FREQUENCY-DOMAIN BLIND SOURCE SEPARATION [J].

Emura, Satoru .

2022 INTERNATIONAL WORKSHOP ON ACOUSTIC SIGNAL ENHANCEMENT (IWAENC 2022), 2022,

← 1 2 3 4 5 →