Convolutive Blind Speech Separation by Decorrelation

被引：0

作者：

Wang, Fuxiang ^{[1
]}

Zhang, Jun ^{[1
]}

机构：

[1] Beihang Univ, Sch Elect & Informat Engn, Beijing 100083, Peoples R China

来源：

ADVANCES IN NEURO-INFORMATION PROCESSING, PT I | 2009年 / 5506卷

关键词：

NONSTATIONARY SOURCES; DIAGONALIZATION; 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：

This paper proposes a new method for convolutive blind speech separation by decorrelation. First, by the design of a FIR separating filter and a whitening process of the observed data, the separation of convolutive speech mixtures are transformed to find a semi-unitary separating matrix. Then we estimate the separating semi-unitary matrix by the semi-unitary joint diagonalization for a set of correlation matrices. And a numerical algorithm for semi-unitary joint diagonalization is proposed. Simulation results of speech separation demonstrate the effectiveness of the new approach.

引用

页码：737 / 744

页数：8

共 50 条

[21] Subband-based blind separation for convolutive mixtures of speech
Araki, S
Makino, S
Aichner, R
Nishikawa, T
Saruwatari, H
IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2005, E88A (12) : 3593 - 3603
[22] Convolutive Blind Signal Separation Spatial Effectiveness in Speech Intelligibility Improvement
Kocinski, J.
Sek, A.
Libiszewski, P.
ACTA PHYSICA POLONICA A, 2011, 119 (6A) : 996 - 999
[23] The role of high frequencies in convolutive blind source separation of speech signals
Jafari, Maria G.
Plumbley, Mark D.
INDEPENDENT COMPONENT ANALYSIS AND SIGNAL SEPARATION, PROCEEDINGS, 2007, 4666 : 488 - +
[24] Quasi-blind source separation algorithm for convolutive mixture of speech
Chu, Yijing
Ding, Heping
Qiu, Xiaojun
2006 IEEE 12TH DIGITAL SIGNAL PROCESSING WORKSHOP & 4TH IEEE SIGNAL PROCESSING EDUCATION WORKSHOP, VOLS 1 AND 2, 2006, : 233 - 238
[25] AN IMROVEMENT IN USING HERMITIAN ANGLEIN CONVOLUTIVE SPEECH BLIND SOURCE SEPARATION
Mahmoodian, Hamid
Soltani, Atefeh
Hashemi, Ali
2013 INTERNATIONAL CONFERENCE ON ELECTRONICS, COMPUTER AND COMPUTATION (ICECCO), 2013, : 368 - 371
[26] BLIND SEPARATION OF CONVOLUTIVE MIXTURES OF SPEECH SOURCES: EXPLOITING LOCAL SPARSITY
Fu, Xiao
Ma, Wing-Kin
2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 4315 - 4319
[27] A convolutive blind signal separation method for joint speech signal separation and echo cancellation
Pan, QF
Aboulnasr, T
Proceedings of the 46th IEEE International Midwest Symposium on Circuits & Systems, Vols 1-3, 2003, : 752 - 755
[28] A Blind Source Separation Approach Based on IVA for Convolutive Speech Mixtures
Jan, Tariqullah
Zafar, Haseeb
Khalil, Ruhulamin
Ashraf, Majid
2016 8TH COMPUTER SCIENCE AND ELECTRONIC ENGINEERING CONFERENCE (CEEC), 2016, : 140 - 145
[29] Blind separation of convolutive mixtures
Ehlers, F
Schuster, HG
40TH MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1 AND 2, 1998, : 1244 - 1247
[30] Blind separation of convolutive mixtures of speech signals using linear combination model
Ohata, M
Mukai, T
Matsuoka, K
ISSPA 2005: The 8th International Symposium on Signal Processing and its Applications, Vols 1 and 2, Proceedings, 2005, : 33 - 36

← 1 2 3 4 5 →