Auditory-based Subband Blind Source Separation using Sample-by-Sample and Infomax Algorithms

被引：0

作者：

Ben Salem, Abderraouf ^{[1
]}

Selouani, Sid-Ahmed ^{[2
]}

Hamam, Habib ^{[3
]}

机构：

[1] Canadian Univ Dubai, Dubai, U Arab Emirates

[2] Univ Moncton, Moncton, NB E8S 1P6, Canada

[3] Univ Moncton, Moncton, NB E1A 3E9, Canada

来源：

WORLD CONGRESS ON ENGINEERING, WCE 2010, VOL I | 2010年

关键词：

blind source separation; subband decomposition; ear model; convolutive sources; Infomax algorithm; CONVOLUTIVE MIXTURES;

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：

We present a new subband decomposition method for the separation of convolutive mixtures of speech. This method uses a sample-by-sample algorithm to perform the subband decomposition by mimicking the processing performed by the human ear. The unknown source signals are separated by maximizing the entropy of a transformed set of signal mixtures through the use of a gradient ascent algorithm. Experimental results show the efficiency of the proposed approach in terms of signal-to-interference ratio. Compared with the fullband method that uses the Infomax algorithm, our method shows an important improvement of the output signal-to-noise ratio when the sensor inputs are severely degraded by additive noise.

引用

页码：651 / 655

页数：5

共 50 条

[41] Blind source separation from hybrid mixture of sub- and super-Gaussian signals by using nonlinear InfoMax principle
Yang, Luxi
He, Zhenya
[J]. Chinese Journal of Electronics, 1999, 8 (03): : 292 - 297
[42] Efficient subband fast adaptive algorithm based-backward blind source separation for speech intelligibility enhancement
Sayoud, Akila
Djendi, Mohamed
[J]. INTERNATIONAL JOURNAL OF SPEECH TECHNOLOGY, 2020, 23 (02) : 471 - 479
[43] Efficient subband fast adaptive algorithm based-backward blind source separation for speech intelligibility enhancement
Akila Sayoud
Mohamed Djendi
[J]. International Journal of Speech Technology, 2020, 23 : 471 - 479
[44] Comparison of blind source separation algorithms for FMRI using a new Matlab toolbox: Gift
Correa, N
Adali, T
Li, YO
Calhoun, VD
[J]. 2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING, 2005, : 401 - 404
[45] Performance of blind source separation algorithms for fMRI analysis using a group ICA method
Correa, Nicolle
Adali, Tulay
Calhoun, Vince D.
[J]. MAGNETIC RESONANCE IMAGING, 2007, 25 (05) : 684 - 694
[46] Blind Source Separation from Single Channel Audio Recording Using ICA Algorithms
Calderon-Piedras, Juan S.
Orjuela-Canon, Alvaro. D.
Sanabria-Quiroga, David A.
[J]. 2014 XIX SYMPOSIUM ON IMAGE, SIGNAL PROCESSING AND ARTIFICIAL VISION (STSIVA), 2014,
[47] Speech intelligibility improvement using convolutive blind source separation assisted by denoising algorithms
Kocinski, Jedrzej
[J]. SPEECH COMMUNICATION, 2008, 50 (01) : 29 - 37
[48] Using piecewise linear nonlinearities in the natural gradient and fastICA algorithms for blind source separation
Chao, Jih-Cheng
Douglas, Scott C.
[J]. 2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12, 2008, : 1813 - +
[49] Two Model-Based EM Algorithms for Blind Source Separation in Noisy Environments
Schwartz, Boaz
Gannot, Sharon
Habets, Emanuel A. P.
[J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2017, 25 (11) : 2209 - 2222
[50] Blind source separation of single-channel statistically correlated mechanical vibration signals based on subband extraction of EEMD
[J]. Meng, Zong, 1600, Chinese Vibration Engineering Society (33):

← 1 2 3 4 5 →