CFP last date
22 April 2024
Reseach Article

A Novel Algorithm for Multichannel Deconvolutive based on hh-Divergence

by Wael M. Khedr, M. E. Abd El-aziz, S. M. Amer
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 57 - Number 10
Year of Publication: 2012
Authors: Wael M. Khedr, M. E. Abd El-aziz, S. M. Amer
10.5120/9149-3394

Wael M. Khedr, M. E. Abd El-aziz, S. M. Amer . A Novel Algorithm for Multichannel Deconvolutive based on hh-Divergence. International Journal of Computer Applications. 57, 10 ( November 2012), 9-14. DOI=10.5120/9149-3394

@article{ 10.5120/9149-3394,
author = { Wael M. Khedr, M. E. Abd El-aziz, S. M. Amer },
title = { A Novel Algorithm for Multichannel Deconvolutive based on hh-Divergence },
journal = { International Journal of Computer Applications },
issue_date = { November 2012 },
volume = { 57 },
number = { 10 },
month = { November },
year = { 2012 },
issn = { 0975-8887 },
pages = { 9-14 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume57/number10/9149-3394/ },
doi = { 10.5120/9149-3394 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T21:00:04.016616+05:30
%A Wael M. Khedr
%A M. E. Abd El-aziz
%A S. M. Amer
%T A Novel Algorithm for Multichannel Deconvolutive based on hh-Divergence
%J International Journal of Computer Applications
%@ 0975-8887
%V 57
%N 10
%P 9-14
%D 2012
%I Foundation of Computer Science (FCS), NY, USA
Abstract

We introduce a novel Algorithm for underdetermined convolutive mixture of source signals. Where the convolution is routinely approximated in the short-time Fourier transform (STFT) domain as linear instantaneous mixing in each frequency band. Each source STFT is given a model inspired from nonnegative matrix factorization (NMF) with the -divergence, this divergence is a family of cost functions parameterized by a two tuning parameters ( and ), and smoothly connect the fundamental Alpha-, Beta- and Gamma-divergences. The proposed family of -multiplicative NMF algorithms is shown to improve robustness separation with respect to noise and outliers. Our decomposition algorithm is applied to stereo audio source separation in various settings, covering blind and supervised separation, music and speech sources, synthetic instantaneous and convolutive mixtures.

References
  1. Amari ,S. 2007. Integration of stochastic models by minimizing ?-divergence. Neural Comput. ,19, 2780- 2796.
  2. Benaroya, L. , Gribonval ,R. , and Bimbot, F. 2003. Non negative sparse representation for Wiener based source separation with a single sensor, in Proc. IEEE Int. Conf. Acoust. , Speech, Signal Process. (ICASSP'03), Hong Kong, pp. 613–616.
  3. Campbell ,D, Roomsim Toolbox [Online]. Available: http://www. mathworks. com/matlabcentral/fileexchange/5184.
  4. Cichocki ,A. , Lee,H. , Kim,Y. D,and Choi ,S . 2008. Nonnegative matrix factorization with ?-divergence. Pattern Recogn. Lett. 29, 1433–1440.
  5. Cichocki ,A. , Sergio ,C. , and Amari, S. 2011. Generalized Alpha-Beta Divergences and Their Application to Robust Nonnegative Matrix Factorization. Entropy, 13, 134-170.
  6. Cichocki, A. , Zdunek, R. , and Amari, S. 2006 . Csiszr's divergences for nonnegative matrix factorization. Family of new algorithms. In Lecture Notes in Computer Science; Springer: Charleston, SC, USA, Volume 3889, pp. 32–39.
  7. Cichocki, A. , Zdunek, R. , Phan ,A. H. , and. 2009 . Nonnegative Matrix and Tensor Factorizations. John Wiley & Sons. Ltd. : Chichester, UK.
  8. Cichocki. A and Amari. S. 2010 . Families of Alpha- Beta- and Gamma- divergences: Flexible and robust measures of similarities. Entropy, 12, pp. 1532–1568.
  9. Example Web Page [Online]. Available: http://www. irisa. fr/metiss/ozerov/demos. html#ieee_taslp09.
  10. (ICA'07),pp. 552-559, Springer. (2007).
  11. Févotte ,C. , Bertin ,N. and Durrieu ,J. L. (2009). Nonnegative matrix factorization with the Itakura-Saito divergence with application to music analysis. Neural Comput. 21, 793–830, (2009).
  12. FitzGerald ,D. , Cranitch ,M. , and Coyle,E,. 2005. Non- negative tensor factorization for sound source separation, in Proc. Irish Signals Syst. Conf. ,Dublin, Ireland, pp. 8–12.
  13. In Signal Separation Evaluation Campaign (SiSEC 2008) (2008)[Online]. Available: http://www. sisec. wiki. irisa. fr.
  14. Neeser F. D. and Massey J. L. ,1993 . Proper complex random processes with applications to information theory. IEEE Trans. Inf. Theory, vol. 39,no. 4, pp. 1293–1302.
  15. Ozerov ,A. , and Févotte,C. 2010. Multichannel Nonnegative Matrix Factorization in Convolutive Mixtures for Audio Source Separation. IEEE transactions on audio, speech, and language processing, vol. 18, no. 3
  16. Parra L. and Spence C. , 2000 . Convolutive blind source separation of nonstationary sources,. IEEE Trans. Speech Audio Process. , vol. 8, no. 3,pp. 320–327.
  17. Parry R. M. and Essa I. A. , 2006 . Estimating the spatial position of spectral components in audio, in Proc. 6th Int. Conf. Ind. Compon. Anal. Blind Signal Separation (ICA'06), Charleston, SC, , pp. 666–673. Mar. (2006).
  18. Sawada H. , Araki S. , and Makino S. ,2007 . Measuring dependence of binwise separated signals for permutation alignment in frequency-domain BSS, in IEEE Int. Symp Circuits Syst. (ISCAS'07), pp. 3247–3250. May 27–30.
  19. Smaragdis P. , 1997. Efficient blind separation ofconvolved sound mixtures, in IEEE Works Applicat. Signal Process Audio Acoust. (WASPAA'97),New Paltz, NY, 4 pp. Oct. (1997).
  20. Vincent ,E. , Sawada ,H. , Bofill ,P. , Makino, S. , and Rosca J. P. , 2007 . First stereo audio source separation evaluation campaign: Data, algorithms and results,Proc. Int. Conf. Ind. Compon. Anal. Blind Source Separation. (2007).
Index Terms

Computer Science
Information Sciences

Keywords

Blind signal separation (BSS) Nonnegative matrix Factorization (NMF) -divergence -NMF ICA