A robust approach to the permutation problem of frequency-domain blind source separation

被引:0
作者
Sawada, H [1 ]
Mukai, R [1 ]
Araki, S [1 ]
Makino, S [1 ]
机构
[1] NTT Corp, NTT Commun Sci Labs, Seika, Kyoto 6190237, Japan
来源
2003 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL V, PROCEEDINGS: SENSOR ARRAY & MULTICHANNEL SIGNAL PROCESSING AUDIO AND ELECTROACOUSTICS MULTIMEDIA SIGNAL PROCESSING | 2003年
关键词
D O I
暂无
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
This paper presents a robust and precise method for solving the permutation problem of frequency-domain blind source separation. It is based on two previous approaches: the direction of arrival estimation approach and the inter-frequency correlation approach. We discuss the advantages and disadvantages of the two approaches, and integrate them to exploit the both advantages. We also present a closed form formula to calculate a null direction, which is used in estimating the directions of source signals. Experimental results show that our method solved permutation problems almost perfectly for a situation that two sources were mixed in a room whose reverberation time was 300 ms.
引用
收藏
页码:381 / 384
页数:4
相关论文
共 12 条
[1]   Natural gradient works efficiently in learning [J].
Amari, S .
NEURAL COMPUTATION, 1998, 10 (02) :251-276
[2]  
ANEMULLER J, 2000, P 2 INT WORKSH IND C, P215
[3]  
Asano F, 2001, INT CONF ACOUST SPEE, P2729, DOI 10.1109/ICASSP.2001.940210
[4]   AN INFORMATION MAXIMIZATION APPROACH TO BLIND SEPARATION AND BLIND DECONVOLUTION [J].
BELL, AJ ;
SEJNOWSKI, TJ .
NEURAL COMPUTATION, 1995, 7 (06) :1129-1159
[5]  
Ikram MZ, 2002, INT CONF ACOUST SPEE, P881
[6]  
Kurita S, 2000, INT CONF ACOUST SPEE, P3140, DOI 10.1109/ICASSP.2000.861203
[7]   An approach to blind source separation based on temporal structure of speech signals [J].
Murata, N ;
Ikeda, S ;
Ziehe, A .
NEUROCOMPUTING, 2001, 41 :1-24
[8]   Convolutive blind separation of non-stationary sources [J].
Parra, L ;
Spence, C .
IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2000, 8 (03) :320-327
[9]  
Sawada H, 2002, NEURAL NETWORKS FOR SIGNAL PROCESSING XII, PROCEEDINGS, P465, DOI 10.1109/NNSP.2002.1030058
[10]  
Sawada H, 2002, INT CONF ACOUST SPEE, P1001