Sound source separation using convolutional mixing and a...

Details Sound source separation using convolutional mixing and a... Sound source separation using convolutional mixing and a...

2006-05-16

2006-05-16

McFadden, Susan (Department: 2655)

Data processing: speech signal processing, linguistics, language

Speech signal processing

For storage or transmission

C704S223000, C381S094100, C381S094200, C381S066000

Reexamination Certificate

active

07047189

ABSTRACT:
Sound source separation, without permutation, using convolutional mixing independent component analysis based on a priori knowledge of the target sound source is disclosed. The target sound source can be a human speaker. The reconstruction filters used in the sound source separation take into account the a priori knowledge of the target sound source, such as an estimate the spectra of the target sound source. The filters may be generally constructed based on a speech recognition system. Matching the words of the dictionary of the speech recognition system to a reconstructed signal indicates whether proper separation has occurred. More specifically, the filters may be constructed based on a vector quantization codebook of vectors representing typical sound source patterns. Matching the vectors of the codebook to a reconstructed signal indicates whether proper separation has occurred. The vectors may be linear prediction vectors, among others.

REFERENCES:
patent: 5026051 (1991-06-01), Lowe et al.
patent: 5052685 (1991-10-01), Lowe et al.
patent: 5138660 (1992-08-01), Lowe et al.
patent: 5208786 (1993-05-01), Weinstein et al.
patent: 5272757 (1993-12-01), Scofield et al.
patent: 5291556 (1994-03-01), Gale
patent: 5436975 (1995-07-01), Lowe et al.
patent: 5448287 (1995-09-01), Hull
patent: 5473343 (1995-12-01), Kimmich et al.
patent: 5487113 (1996-01-01), Mark et al.
patent: 5543887 (1996-08-01), Akashi
patent: 5727122 (1998-03-01), Hosoda et al.
patent: 5768393 (1998-06-01), Mukojima et al.
patent: 5862229 (1999-01-01), Shimizu
patent: 5867654 (1999-02-01), Ludwig et al.
patent: 5872566 (1999-02-01), Bates et al.
patent: 5993318 (1999-11-01), Kousaki
patent: 6040831 (2000-03-01), Nishida
patent: 6046772 (2000-04-01), Howell
patent: 6081266 (2000-06-01), Sciammarella
patent: 6088031 (2000-07-01), Lee et al.
patent: 6097383 (2000-08-01), Gaughan et al.
patent: 6097390 (2000-08-01), Marks
patent: 6122381 (2000-09-01), Winterer
patent: 6185309 (2001-02-01), Attias
patent: 6647119 (2003-11-01), Slezak
Independent Component Analysis: Theory and Applications, By Te-Won Lee, Computational Neurobiology Laboratory Kluwer Academic Publishers 1998.
A New Learning Algorithm for Blind Single Separation, By S. Amari et al. MIT Press 1996, pp. 757-763.
Independent Factor Analysis. Sloan Center for Theoretical Neuroboilogy and W.M. Keck Foundation Center for Integrative Neurosciance, University of Calf. San Francisco. Neural Computation, in press. By H. Attias pp. 1-34.
Blind Source Separation and Deconvolution: The Dynamic Component Analysis Algorithm by H. Attias et al., Sloan Center for Theoretical Neuroboilogy and W.M. Keck Foundation Center for Integrative Neurosciance, University of Calf. San Francisco. Neural Computation 10, (1998) pp. 1-37.
Blind Separation and Blind Deconvolution: An Information-Theoretic Approach. By Anthony J. Bell et al., Computational Neurobiology Laboratory, The Salk Institute. 4 pages.
Explicit Speech Modeling for Distant-Talker Signal Acquisition. By Michael S. Brandstein. Harvard Intelligent Multi-Media Environment Laboratory (HIMMEL) Dec. 1998. pp. 1-19.
On The Use of Explicit Speech Modeling In Microphone Array Applications. By Michael S. Brandstein. Division of Engineering and Applied Sciences Harvard University. 4 pages.
Theory and Applications of Acoustic Signal Processing For Telecommunication. Nonlinear, Model-Based Microphone Array Speech Enhancement. By Michael S. Brandstein. Division of Engineering and Applied Sciences Harvard University. pp. 1-21.
Blind Signal Separation: Statistical Principles. By Jean-Francois Cardoso, et al. pp. 1-16.
Infomax and Maximum Likelihood for Blind Source Separation by Jean-Francois Cardoso. Member, IEEE. IEEE Signal Processing Letters, vol. 4, No. 4, Apr. 1997. 5 pages.
Blind Separation of Source, Part I: An Adaptive Algorithm Based on Neuromimetic Architecture. By Christian Jutten et al., Received Apr. 2, 1990, Revised Oct. 24, 1990 and Feb. 21, 1991. pp. 1-10.
Independent Component Analysis Using an Extended Infomax Algorithm for Mixed Subgaussian and Supergaussian Sources. By Te-Won Lee et al. Neural Computation 11, pp. 417-441 (1999) Massachusetts Institute of Technology.
A Context-Sensitive Generalization of ICA by Barak A. Perlmutter et al. Siemens Corporate Research, Princeton New Jersey USA. 7 pages.
Networks For the Separation of Sources that are Superimposed and Delayed. By John C. Platt et al. Synaptics, Inc. pp. 730-737.
Multi-Channel Signal Separation by Decorrelation. By Ehud Weinstein et al., IEEE Transactions on Speech and Audio Processing, Oct. 1993, vol. 1, No. 4 pp. 405-413.
Criteria for Multichannel Signal Separation. By Daniel Yellin et al. IEEE Transactions on Signal Processing, Aug. 1994, vol. 42, No. 8. pp. 2158-2168.
Blind Source Separation by Separation by Sparse Decomposition in a Signal Dictionary. By M. Zibulevsky et al. University of Mexico pp. 1-29.
Amari S., Cichocki A. and Yang H. H. “A New Learning Algorithm for Blind Separation”. In D.S. Touretzky, M.C. Mozer and M.E. Hasselmo, editors,Advances in Neural Information Processing Systems, vol. 8, pp. 757-763. MIT Press, 1996.
H. Attias, “Independent Factor Analysis,”Neual Computationvol. 11, No. 4, pp. 803-851, 1999.
H. Attias and C.E. Schreiner, “Blind Source Separatin and Deconvolution: The Dynamic Component Analysis Algorithm, ”Neural Computation, vol. 10, pp. 1373-1424, 1998.
M. Brandstein, “Explicit Speech Modeling for Distant-Talker Signal Acquisition, ” reprint, 1998.
M. Brandstein, “On the Use of Explicit Speech Modeling in Microphone Array Applications, ” InProceedings of ICASSP, pp. 3613-3616, 1998.
M. Brandstein and S. Griebel, “Nonlinear, Model-Based Microphone Array Speech Enhancement.” InTheory and Applications of Acoustic Signal Processing for Telecommunications, J. Benesty nand S. Gay editors, Kluwer Academic Publishers, 2000.
J. Cardoso, “Blind Signal Separation: Statistical Principles.” InProceedings of the IEEEvol. 90, No. 8, pp. 2009-2026, 1998.
J. Cardoso, “Infomax and Maximum Likelihood for Blind Source Separation.” InIEEE Signal Processing letters, vol. 4, No. 4, pp. 112-114, 1997.
C. Jutten and J. Herault, “Blind Separation of Source, Part I: An Adaptive Algorithm Based on Neuromimetic Architecture.” InSignal Processing, vol. 24, No. 1, pp. 10-10, 1991.
T.W. Lee, “Independent Component Analysis: Theory and Applications,” Kluwer Academic Publishers, 210 pages, 1998.
T.W. Lee, M. Girolami and T. Sejnowski, “Independent Component Analysis Using an Extented Infomax Algorithm for Mixed Subgaussian and Supergaussian Sources.” InNeural Computation, vol. 11, pp. 417-441, 1999.
B. Pearlmutter and L. Parra, “A Context Sensitive Generalization of ICA.” In M. Mozer, M. Jordan & T. Petsche, editors, Advances in Neural Information Processing, vol. 9, pp. 613-619, Cambridge MA, 1997. MIT Press.
J. Platt and F. Faggin, “Networks for the Separation of Sources that aree Superimposed and Delayed.” InProceedings of the Neural Information Processing Systems Conference, 1991,k pp. 730-737, 1991.
E. Weinstein, M. Feder and A. Oppenheim, “Multi-Channel Signal Separation by Decorrelation.” InIEEE Transactions on Speech and Audio Processing, vol. 1, No. 4, pp. 405-413, 1993.
D. Yellin and E. Weinstein, “Criteria for Multichannel Signal Separation.” InIEEE Transactions on Signal Processing, vol. 42, No. 8, pp. 2158-2167, 1994.
M. Zibulevsky and B. Pearlmutter, “Blind Source Separation by Sparse Decomposition in a Signal Dictionary.” University of New Mexico Technical Report, No. CS99-1, 1999.

Affiliated with

Also associated with

Rating

Sound source separation using convolutional mixing and a... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Sound source separation using convolutional mixing and a..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Sound source separation using convolutional mixing and a... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3647021