Fundamental limitation of frequency domain blind source separation for convolutive mixture of speech

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 5, Issue , 2001, Pages 2737-2740

  Araki, Shoko ^a   Makino, Shoji ^a   Nishikawa, Tsuyoki ^b   Saruwatari, Hiroshi ^b  

^a Nippon Telegraph and Telephone Corporation   (Japan)

^b NARA INSTITUTE OF SCIENCE AND TECHNOLOGY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC SIGNAL PROCESSING; CALCULATIONS; CONVOLUTION; FAST FOURIER TRANSFORMS; FREQUENCY DOMAIN ANALYSIS; JAMMING; REVERBERATION; SAMPLING; SPEECH TRANSMISSION; TRANSFER FUNCTIONS;

JAMMER SIGNALS; REVERBERATION TIME; SAMPLING FREQUENCY;

BLIND SOURCE SEPARATION;

EID: 0034848298     PISSN: 15206149     EISSN: None     Source Type: Journal    
DOI: 10.1109/ICASSP.2001.940212     Document Type: Article

References (10)

1. An information-maximization approach to blind separation and blind deconvolution
2. Unsupervised adaptive filtering
3. Independent component analysis - Theory and applications
4. Real world blind separation of convolved non-stationary signals
5. A method of ICA in time-frequency domain
6. Blind separation of convolved mixtures in the frequency domain
7. Convolutive blind separation of non-stationary sources
8. Exploring permutation inconsistency in blind separation of speech signals in a reverberant environment
9. Evaluation of blind signal separation method using directivity pattern under reverberant conditions
10. Multi-channel signal separation by decorrelation