Two-microphone separation of speech mixtures

IEEE Transactions on Neural Networks

Volumn 19, Issue 3, 2008, Pages 475-492

  Pedersen, Michael Syskind ^a   Wang, DeLiang ^b   Larsen, Jan ^c   Kjems, Ulrik ^a  

^a OTICON A S   (Denmark)

^b Ohio State University   (United States)

^c TECHNICAL UNIVERSITY OF DENMARK   (Denmark)

Author keywords

Ideal binary mask; Independent component analysis (ICA); Time frequency (T F) masking; Underdetermined speech separation

Indexed keywords

INDEPENDENT COMPONENT ANALYSIS; MICROPHONES; REVERBERATION; SOUND RECORDING; SPEECH PROCESSING;

BINARY TIME-FREQUENCY MASKING; IDEAL BINARY MASK; UNDERDETERMINED SPEECH SEPARATION;

BLIND SOURCE SEPARATION;

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; HUMAN; PRINCIPAL COMPONENT ANALYSIS; SIGNAL PROCESSING; SOUND;

ALGORITHMS; HUMANS; NEURAL NETWORKS (COMPUTER); PRINCIPAL COMPONENT ANALYSIS; SIGNAL PROCESSING, COMPUTER-ASSISTED; SOUND;

EID: 40949096929     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/TNN.2007.911740     Document Type: Article

References (69)

1. E. C. Cherry, "Some experiments on the recognition of speech, with one and two ears," J. Acoust. Soc. Amer., vol. 25, no. 5, pp. 975-979, Sep. 1953.
2. S. Haykin and Z. Chen, "The cocktail party problem," Neural Comput. vol. 17, pp. 1875-1902, Sep. 2005.
3. L. K. Hansen, "Blind separation of noisy image mixtures," in in Advances in Independent Component Analysis, Perspectives in Neural computing, M. Girolami, Ed. New York: Springer-Verlag, 2000, pp. 165-187, ch. 9.
4. K. Torkkola, "Blind separation of delayed and convolved sources," in in Unsupervised Adaptive Filtering, Blind Source Separation, S. Haykin, Ed. New York: Wiley, Jan. 2000, vol. 1, ch. 8, pp. 321-375.
5. J. M. Peterson and S. Kadambe, "A probabilistic approach for blind source separation of underdetermined convolutive mixtures," in Proc. IEEE Int. Conf. Acoust. Speech Signal Process., 2003, vol. 6, pp. VI-581-VI-584.
6. A. K. Barros, T. Rutkowski, F. Itakura, and N. Ohnishi, "Estimation of speech embedded in a reverberant and noisy environment by independent component analysis and wavelets," IEEE Trans. Neural Netw., vol. 13, no. 4, pp. 888-893, Jul. 2002.
7. S. Araki, S. Makino, A. Blin, R. Mukai, and H. Sawada, "Blind separation of more speech than sensors with less distortion by combining sparseness and ICA," in Proc. Int. Workshop Acoust. Echo Noise Control, Kyoto, Japan, Sep. 2003, pp. 271-274.
8. O. Yilmaz and S. Rickard, "Blind separation of speech mixtures via time-frequency masking," IEEE Trans. Signal Process., vol. 52, no. 7, pp. 1830-1847, Jul. 2004.
9. R. K. Olsson and L. K. Hansen, "Blind separation of more sources than sensors in convolutive mixtures," in Proc. IEEE Int. Conf. Acoust. Speech Signal Process., 2006, vol. V, pp. 657-660 [Online]. Wvailable: http:www2.imm.dtu.dk/pubdb/p.php?4321
10. A. Hyvärinen, J. Karhunen, and E. Oja, Independent Component Analysis. New York: Wiley, 2001.
11. C. Jutten and J. Herault, "Blind separation of sources, Part I: An adaptive algorithm based on neuromimetic architecture," Signal Process., vol. 24, no. 1, pp. 1-10, 1991.
12. P. Comon, E. Moreau, and L. Rota, "Blind separation of convolutive mixtures: A contrast-based joint diagonalization approach," presented at the 3rd Int. Conf. Independent Component Anal., San Diego, CA, Dec. 9-13, 2001.
13. A. J. Bell and T. J. Sejnowski, "An information-maximization approach to blind separation and blind deconvolution," Neural Comput., vol. 7, no. 6, pp. 1129-1159, 1995.
14. A. Hyvärinen and E. Oja, "Independent component analysis: Algorithms and applications," Neural Netw., vol. 13, no. 4-5, pp. 411-430, 2000.
15. L. Molgedey and H. Schuster, "Separation of independent signals using time-delayed correlations," Phys. Rev. Lett., vol. 72, no. 23, pp. 3634-3637, 1994.
16. T. Kolenda, L. Hansen, and J. Larsen, "Signal detection using ICA: Application to chat room topic spotting," in Proc. Int. Conf. Independent Component Anal., 2001, pp. 540-545 [Online]. Available: http://www.imm.dtu.dk/pubdb/p.php?826
17. L. K. Hansen, J. Larsen, and T. Kolenda, "On independent component analysis for multimedia signals," in Multimedia Image and Video Processing, L. Guan, S. Kung, and J. Larsen, Eds. Boca Raton, FL: CRC Wress, 2000, pp. 175-199 [Online]. Available: http:www.imm.dtu.dk/pubdb/ p.php?627
18. K. Matsuoka, M. Ohya, and M. Kawamoto, "A neural net for blind separation of nonstationary signals," Neural Netw., vol. 8, no. 3, pp. 411-419, 1995.
19. L. Parra and C. Spence, "Convolutive blind separation of non-stationary sources," IEEE Trans. Speech Audio Process., vol. 8, no. 3, pp. 320-327, May 2000.
20. D. Luengo, I. Santamaria, L. Vielva, and C. Pantaleon, "Underdetermined blind separation of sparse sources with instantaneous and convolutive mixtures," in Proc. IEEE 13th Workshop Neural Netw. Signal Process. 2003, pp. 279-288.
21. S. Arberet, R. Gribonval, and F. Bimbot, "Arobust method to count and locate audio sources in a stereophonic linear instantaneous mixture," in Proc. Int. Conf. Independent Component Anal., 2006, pp. 536-543.
22. D. B. Rowe, "A Bayesian approach to blind source separation," J. Interdiscip. Math., vol. 5, no. 1, pp. 49-76, 2002.
23. P. Bofill and M. Zibulevsky, "Underdetermined blind source separation using sparse representations," Signal Process., vol. 81, pp. 2353-2362, 2001
24. N. Roman, D. L. Wang, and G. J. Brown, "Speech segregation based on sound localization," J. Acoust. Soc. Amer., vol. 114, no. 4, pp. 2236-2252, Oct. 2003.
25. S. Winter, H. Sawada, S. Araki, and S. Makino, "Overcomplete BSS for convolutive mixtures based on hierarchical clustering," in Proc. Int. Conf. Independent Component Anal., Granada, Spain, Sep. 22-24, 2004, pp. 652-660.
26. P. D. O'Grady, B. A. Pearlmutter, and S. T. Rickard, "Survey of sparse and non-sparse methods in source separation," Int. J. Imag. Syst. Technol., Special Issue on Blind Source Separation and Deconvolution in Imaging and Image Processing, to be published.
27. S. T. Roweis, "Factorial models and refiltering for speech separation and denoising," in Proc. EUROSPEECH Conf., Geneva, Sep. 2003, pp. 1009-1012.
28. A. Jourjine, S. Rickard, and O. Yilmaz, "Blind separation of disjoint orthogonal signals: Demixing N sources from 2 mixtures," in Proc. Int. Conf. Acoust. Speech Signal Process., Istanbul, Turkey, Jun. 2000, vol. V, pp. 2985-2988.
29. D. L. Wang and G. J. Brown, Computational Auditory Scene Analysis: Principles, Algorithms, and Applications. Hoboken, NJ:WIley/IEEE Press, 2007.
30. D. L. Wang and G. J. Brown, "Separation of speech from interfering sounds based on oscillatory correlation," IEEE Trans. Neural Netw. vol. 10, no. 3, pp. 684-697, May 1999.
31. A. S. Bregman, Auditory Scene Analysis, 2nd ed. Cambridge, MA: MIT Press, 1990.
32. D. L. Wang, "On ideal binary mask as the computational goal of auditory scene analysis," in Speech Separation by Humans and Machines, P. Divenyi, Ed. Norwell, MA: Kluwer, 2005, pp. 181-197.
33. B. C. J. Moore, An Introduction to the Psychology of Hearing, 5th ed. New York: Academic, 2003.
34. G. Hu and D. L. Wang, "Monaural speech segregation based on pitch tracking and amplitude modulation," IEEE Trans. Neural Netw., vol. 15, no. 5, pp. 1135-1150, Sep. 2004.
35. S. Roweis, "One microphone source separation," in Proc. Neural Inf. Process. Syst., 2000, pp. 793-799.
36. P. Li, Y. Guan, B. Xu, and W. Liu, "Monaural speech separation based on computational auditory scene analysis and objective quality assessment of speech," IEEE Trans. Audio Speech Lang. Process., vol. 14, no. 6, pp. 2014-2023, Nov. 2007.
37. S. Araki, H. Sawada, R. Mukai, and S. Makino, "Underdetermined blind sparse source separation for arbitrarily arranged multiple sensors," Signal Process., vol. 87, no. 8, pp. 1833-1847, 2007.
38. P. Aarabi and G. Shi, "Phase-based dual-microphone robust speech enhancement," IEEE Trans. Syst. Man Cybern. B, Cybern., vol. 34, no. 4, pp. 1763-1773, Aug. 2004.
39. S. Araki, S. Makino, H. Sawada, and R. Mukai, "Reducing musical noise by a fine-shift overlap-add method applied to source separation using a time-frequency mask," in Proc. Int. Conf. Acoust. Speech Signal Process., Mar. 18-23, 2005, vol. III, pp. 81-84.
40. S. Araki, S. Makino, H. Sawada, and R. Mukai, "Underdetermined blind separation of convolutive mixtures of speech with directivity pattern based mask and ICA," in Proc. Int. Conf. Independent Component Anal. Sep. 22-24, 2004, pp. 898-905.
41. D. Kolossa and R. Orglmeister, "Nonlinear postprocessing for blind speech separation," in Proc. Int. Conf. Independent Component Anal. Granada, Spain, Sep. 22-24, 2004, pp. 832-839.
42. H. Sawada, S. Araki, R. Mukai, and S. Makino, "Grouping separated frequency components by estimating propagation model parameters in frequency-domain blind source separation," IEEE Trans. Audio Speech Lang. Process., vol. 15, no. 5, pp. 1592-1604, Jul. 2007.
43. M. S. Pedersen, D. L. Wang, J. Larsen, and U. Kjems, "Overcomplete blind source separation by combining ICA and binary time-frequency masking," in Proc. Mach. Learn. Signal Process. Workshop, Mystic, WT, Sep. 28-30, 2005, pp. 15-20 [Online]. Available: http://www.imm. dtu.dk/pubdb/p.php?3894
44. M. S. Pedersen, T. Lehn-Schioler, and J. Larsen, "Blues from music: Blind underdetermined extraction of sources from music," in Proc. Int. Conf. Independent Component Anal., 2006, pp. 392-399 [Online]. Wvailable: http://www.imm.dtu.dk/pubdb/p.php?4060
45. M. S. Pedersen, D. L. Wang, J. Larsen, and U. Kjems, "Separating underdetermined convolutive speech mixtures," in Proc. Int. Conf. Independent Component Anal., 2006, pp. 674-681 [Online]. Available: http://www.imm.dtu.dk/pubdb/p.php?4068
46. M. Ito, Y. Takeuchi, T. Matsumoto, H. Kudo, M. Kawamoto, T. Mukai, and N. Ohnishi, "Moving-source separation using directional microphones," in Proc. Int. Symp. Signal Process. Inf. Theory, Dec. 2002, pp. 523-526.
47. G. Cauwenberghs, M. Stanacevic, and G. Zweig, "Blind broadband source localization and separation in miniature sensor arrays," in Proc. IEEE Int. Symp. Circuits Syst., May 6-9, 2001, vol. 3, pp. 193-196.
48. M. S. Brandstein and D. B. Ward, Eds., Microphone Arrays, ser. Digital Signal Processing. New York: Springer-Verlag, 2001.
49. S. Araki, S. Makino, R. Mukai, and H. Saruwatari, "Equivalence between frequency domain blind source separation and frequency domain adaptive null beamformers," in Proc. Eurospeech, Aalborg, Denmark, Sep. 2001, pp. 2595-2598.
50. R. D. Patterson, "The sound of a sinusoid: Spectral models," J. Acoust. Soc. Amer., vol. 96, pp. 1409-1418, May 1994.
51. A. Härmä, M. Karjalainen, L. Savioja, V. Välimäki, U. K. Laine, and J. Huopaniemi, "Frequency-warped signal processing for audio applications," J. Audio Eng. Soc., vol. 48, no. 11, pp. 1011-1031, Nov. 2000.
52. N. Murata, S. Ikeda, and A. Ziehe, "An approach to blind source separation based on temporal structure of speech signals," Neurocomputing, vol. 41, no. 1-4, pp. 1-24, 2001.
53. J. Anemüller and B. Kollmeier, "Amplitude modulation decorrelation for convolutive blind source separation," in Proc. 2nd IEEE Int. Workshop Independent Component Anal. Signal Separat., Helsinki, Finland, Jun. 2000, pp. 215-220.
54. W. M. Hartmann, Signals, Sound, and Sensation. New York: Springer-Verlag, 1998.
55. G. H. Golub and C. F. van Loan, Matrix Computations, 3rd ed. Baltimore, MD: The Johns Hopkins University Press, 1996.
56. D. P. W. Ellis, "Evaluating speech separation systems," in in Speech Separation by Humans and Machines, P. Divenyi, Ed. Norwell, MA: Kluwer, 2005, ch. 20, pp. 295-304.
57. M. S. Pedersen, D. L. Wang, J. Larsen, and U. Kjems, "Two-microphone separation of speech mixtures [demo]," Jan. 2007 [Online]. Available: http://www.imm.dtu.dk/pubdb/p.php?4400
58. M. S. Pedersen, D. L. Wang, J. Larsen, and U. Kjems, "Two-microphone separation of speech mixtures [source code]," Jan. 2007 [Online]. Wvailable: http://www.imm.dtu.dk/pubdb/p.php?4399
59. H. Nielsen, "UCMINF - An algorithm for unconstrained, nonlinear optimization," IMM, Tech. Univ. Denmark, Kgs. Lyngby, Denmark, Tech. Wep. IMM-TEC-0019, 2001 [Online]. Available: http:www.imm.dtu.dk/pubdb/ p.php?642
60. T. Kolenda, S. Sigurdsson, O. Winther, L. K. Hansen, and J. Larsen, "DTU: Toolbox," Lyngby, Denmark, 2002 [Online]. Available: http://www.imm.dtu.dk/pubdb/p.php?4043
61. F. J. Harris, "On the use of windows for harmonic analysis with the discrete fourier transform," Proc. IEEE, vol. 66, no. 1, pp. 51-83, Jan. 1978.
62. J.-F. Cardoso and A. Souloumiac, "Blind beamforming for non Gaussian signals," Inst. Electr. Eng. Proc. F, vol. 140, no. 6, pp. 362-370, Dec. 1993.
63. WCA Central, [Online]. Available: http://www.tsi.enst.fr/icacentral/ algos.html
64. F. Asano, Y. Motomura, H. Asoh, and T. Matsui, "Effect of PCA in blind source separation," in Proc. 2nd Int. Workshop Independent Component Anal./Blind Source Separat., P. Pajunen and J. Karhunen, Eds., Helsinki, Finland, Jun. 19-22, 2000, pp. 57-62.
65. N. Roman, S. Srinivasan, and D. L. Wang, "Binaural segregation in multisource reverberant environments," J. Acoust. Soc. Amer., vol. 120, no. 6, pp. 4040-4051, 2006.
66. C. Liu, B. C. Wheeler, W. D. O. Brien, C. R. Lansing, R. C. Bilger, D. L. Jones, and A. S. Feng, "A two-microphone dual delay-line approach for extraction of a speech sound in the presence of multiple interferers," J. Acoust Soc. Amer., vol. 110, pp. 3218-3231, 2001.
67. H. Sawada, R. Mukai, S. Araki, and S. Makino, "A robust and precise method for solving the permutation problem of frequency-domain blind source separation," IEEE Trans. Speech Audio Process., vol. 12, no. 5, pp. 530-538, Sep. 2004.
68. S. C. Thompson, "Directional patterns obtained from two or three microphones," Knowles Electronics, Tech. Rep., Sep. 29, 2000.
69. J. G. Proakis and D. G. Manolakis, Digital Signal Processing. Englewood Cliffs, NJ: Prentice-Hall, 1996.