Multichannel signal separation for cocktail party speech recognition: A dynamic recurrent network

Neurocomputing

Volumn 49, Issue 1-4, 2002, Pages 299-314

  Choi, Seungjin ^a   Hong, Heonseok ^b   Glotin, Heré ^c   Berthommier, Frédéric ^c  

^a Pohang University of Science and Technology (POSTECH)   (South Korea)

^b Chungbuk National University   (South Korea)

^c GRENOBLE INSTITUTE OF TECHNOLOGY   (France)

Author keywords

Blind signal separation; Coctail party problem; Dynamic recurrent networks; Multichannel signal separation; Speech recognition

Indexed keywords

ACOUSTIC SIGNAL PROCESSING; LEARNING ALGORITHMS; PROBLEM SOLVING; SPEECH RECOGNITION;

MULTICHANNEL SIGNAL SEPARATIONS (MSS);

RECURRENT NEURAL NETWORKS;

ALGORITHM; ARTICLE; CONTROLLED STUDY; ERROR; LEARNING; PRIORITY JOURNAL; SIGNAL PROCESSING; SPEECH; TECHNIQUE; TIME; WORD RECOGNITION;

EID: 0036952998     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0925-2312(02)00522-2     Document Type: Article

References (20)

1. S. Amari, Natural gradient works efficiently in learning, Neural Comput. 10 (2) (1998) 251-276.
2. N. Charkani, Y. Deville, Self-adaptive separation of convolutively mixed signals with a recursive structure-part I: stability analysis and optimization of asymptotic behaviour, Signal Process. 73 (3) (1999) 255-266.
3. S. Choi, A. Cichocki, Adaptive blind separation of speech signals: cocktail party problem, Proceedings of International Conference on Speech Processing, 1997, pp. 617-622.
4. S. Choi, H. Hong, H. Glotin, F. Berthommier, Multichannel signal separation for cocktail party speech recognition: a dynamic recurrent network, Proceedings of ICSLP, Beijing, China, 2000.
5. S. Choi, Y. Lyu, F. Berthommier, H. Glotin, A. Cichocki, Blind separation of delayed and superimposed acoustic sources: learning algorithms and experimental study, Proceedings of the International Conference on Speech Processing, 1999, pp. 109-113.
6. P. Comon, Independent component analysis, a new concept? Signal Process. 36 (3) (1994) 287-314.
7. M. Girolami, C. Fyfe, A temporal model of linear anti-hebbian learning, Neural Process. Lett. 4 (3) (1996) 139-148.
8. H. Glotin, F. Berthommier, E. Tessier, A CASA-labelling model using the localication cue for robust cocktail party speech recognition, Proceedings of the EUROSPEECH, 1999.
9. H. Hermansky, M. Morgan, RASTA processing of speech, IEEE Trans. Speech Audio Process. 2 (4) (1994) 578-589.
10. C. Jutten, J. Herault, Blind separation of sources, part I: an adaptive algorithm based on neuromimetic architecture, Signal Process. 24 (1991) 1-10.
11. R.H. Lambert, Multichannel blind deconvolution: FIR matrix algebra and separation of multipath mixtures, Ph.D. Thesis, University of Southern California, May, 1996.
12. T.-W. Lee, A. Bell, R. Lambert, Blind separation of delayed and convolved sources, Adv. Neural Inform. Process. Systems 9 (1997) 758-764.
13. R. Liu, H. Luo, Direct blind separation of independent non-gaussian signals with dynamic channels, Proceedings of the International Workshop on Cellular Neural Networks and their Applications, London, UK, 1998, pp. 34-37.
14. N. Murata, S. Ikeda, Z. Andreas, An approach to blind source separation based on temporal structure of speech signals, Technical Report BSIS-98-2, Brain-style Information Systems Research Group, BSI, RIKEN, 1998.
15. L.C. Parra, C. Spence, Convolutive blind source separation of non-stationary sources, IEEE Trans. Speech Audio Process. 8 (3) (2000) 320-327.
16. P. Smaragdis, Information-theoretic approaches to source separation, Master's Thesis, Massachusetts Institute of Technology, Cambridge, MA, 1997.
17. E. Tessier, F. Berthommier, H. Glotin, S. Choi, A model of source segregation using the localization cue for robust cocktail-party speech recognition, Proceedings of the International Conference on Speech Processing, 1999, pp. 97-102.
18. K. Torkkola, Blind separation of convolved sources based on information maximization, Proceedings of the IEEE Workshop on Neural Networks for Signal Processing, 1996, pp. 423-432.
19. K.-C. Yen, Y. Zhao, Adaptive co-channel speech separation and recognition, IEEE Trans. Speech Audio Process. 7 (2) (1999) 138-151.
20. J. Zhu, X.-R. Cao, R. Liu, Blind source separation based on output independence-theory and implementation, Proceedings of the International Symposium of Nonlinear Theory and Applications, 1995, pp. 97-102.