Skip to main content
Springer Nature Link
Log in

Determined Blind Source Separation Combining Independent Low-rank Matrix Analysis with Optimized Parameters and Q-learning

  • Published:
Circuits, Systems, and Signal Processing Aims and scope Submit manuscript

Abstract

This study utilizes Q-learning to dynamically change the optimized parameters of independent low-rank matrix analysis (ILRMA). Notably, ILRMA, which combines independent vector analysis and non-negative matrix factorization, is a novel methodology adopted to realize multichannel blind source separation (BSS). In previous studies, ILRMA has used optimized parameters to improve separation efficiency. In this study, however, an optimized parameter is obtained from the parametric majorization–equalization algorithm, which adjusts the convergence speed to avoid poor local solutions. Two other optimized parameters are obtained using the isotropic complex Student’s t-distribution, which adjusts the probability distribution to conform to the target mixed audio source distribution. To further improve the performance of BSS, this paper proposes a Q-learning off-policy temporal difference control algorithm (reinforcement learning) to dynamically change the three optimized parameters. To ensure the simplicity and efficiency of Q-learning, n-armed bandits are used to replace traditional high-dimensional Q-tables. Furthermore, experiments are conducted using instruments and vocal multichannel BSS tasks. The results confirm the validity of the proposed method.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

Data Availability

The datasets generated during the analysis and the course of the study are available upon reasonable request from the corresponding authors.

References

  1. S. Araki et al., The 2011 signal separation evaluation campaign (SiSEC2011): audio source separation, in Latent variable analysis and signal separation. LVA/ICA 2012. Lecture Notes in Computer Science. ed. by F. Theis, A. Cichocki, A. Yeredor, M. Zibulevsky (Berlin, Heidelberg, Springer, 2012)

    Google Scholar 

  2. P. Comon, C. Jutten, J. Herault, Blind separation of sources, part II: problem statement. Signal Process. 24, 11–20 (1991)

    Article  MATH  Google Scholar 

  3. P. Comon, Independent component analysis, a new concept? Signal Process. 36, 287–314 (1994)

    Article  MATH  Google Scholar 

  4. J.-F. Cardoso, Infomax and maximum likelihood for blind source separation. IEEE Signal Process. Lett. 4(4), 112–114 (1997)

    Article  Google Scholar 

  5. C. Févotte, N. Bertin, J.-L. Durrieu, Non-negative matrix factorization with the Itakura–Saito divergence: with application to music analysis. Neural Comput. 21(3), 793–830 (2009)

    Article  MATH  Google Scholar 

  6. P. Georgiev, F. Theis, A. Cichocki, H. Bakardjian, Sparse component analysis: a new tool for data mining, in Data Mining in Biomedicine Springer Optimization and Its Applications. ed. by P.M. Pardalos, V.L. Boginski, A. Vazacopoulos (Springer, Boston, 2007)

    Google Scholar 

  7. X. He, T. Zhu, ICA of noisy music audio mixtures based on iterative shrinkage denoising and fastICA using rational nonlinearities. Circuits Syst Signal Process 33, 1917–1956 (2014)

    Article  Google Scholar 

  8. X. He, F. He, A. He, Super-Gaussian BSS using fast-ICA with Chebyshev–Pade approximant. Circuits Syst Signal Process 37, 305–341 (2018)

    Article  MATH  Google Scholar 

  9. D.R. Hunter, K. Lange, Quantile regression via an MM algorithm. J. Comput. Graph. Statistics 9(1), 60–77 (2000)

    MathSciNet  Google Scholar 

  10. D.R. Hunter, K. Lange, A tutorial on MM algorithms. Am. Stat. 58(1), 30–37 (2004)

    Article  MathSciNet  Google Scholar 

  11. M.I. Hossain, M.S. Islam, M.T. Khatun et al., Dual-transform source separation using sparse non-negative matrix factorization. Circuits Syst Signal Process 40, 1868–1891 (2021)

    Article  Google Scholar 

  12. C. Jutten, J. Herault, Blind separation of sources, Part I: an adaptive algorithm based on neuromimetic architecture. Signal Process. 24, 1–20 (1991)

    Article  MATH  Google Scholar 

  13. C. Jutten, H. L. Nguyen Thi, E. Dijkstra, E. Vittoz, J. Caelen, Blind separation of sources, an algorithm for separation of convolutive mixtures. in International Workshop on High Order Statistics, Chamrousse, France, July 1991, pp 273–276 (1991)

  14. T. Kim, T. Eltoft, T. W. Lee (2006) Independent vector analysis: An extension of ICA to multivariate components. In: 6th International Conference Source Independent Component Analysis and Blind Signal Separation: Separation Springer, 165–172 (2006)

  15. K. Kamo, Y. Mitsui, Y. Kubo, N. Takamune, D. Kitamura, H. Saruwatari, Y. Takahashi, K. Kondo, Joint-diagonalizability-constrained multichannel non-negative matrix factorization based on time-variant multivariate complex sub-Gaussian distribution. Signal Process. 188, 108183 (2021)

    Article  Google Scholar 

  16. D. Kitamura, N. Ono, H. Sawada, H. Kameoka, H. Saruwatari, Determined blind source separation unifying independent vector analysis and non-negative matrix factorization. IEEE/ACM Trans. Audio Speech Lang. Process. 24(9), 1626–1641 (2016)

    Article  Google Scholar 

  17. D. Kitamura, N. Ono, H. Sawada, H. Kameoka, H. Saruwatari, Determined blind source separation with independent low-rank matrix analysis, in Audio Source Separation. ed. by S. Makino (Switzerland, Springer, Cham, 2018), pp.125–155

    Chapter  Google Scholar 

  18. D. Lee, H. Seung, Algorithms for non-negative matrix factorization. Adv. Neural Inf. Process. Syst. 13, 556–562 (2001)

    Google Scholar 

  19. K. Mohanaprasad, P. Arulmozhivarman, Wavelet-based ICA using maximum likelihood estimation and information-theoretic measure for acoustic echo cancellation during double talk situation. Circuits Syst Signal Process 34, 3915–3931 (2015)

    Article  MathSciNet  Google Scholar 

  20. Y. Mitsui, D. Kitamura, N. Takamune, H. Saruwatari, Y. Takahashi, K. Kondo Independent low-rank matrix analysis based on parametric majorization-equalization algorithm. in 2017 IEEE 7th Int. Workshop Comput. Adv. Multi-Sensor Adaptive Process. (CAMSAP) (2017)

  21. S. Mogami, D. Kitamura, Y. Mitsui, N. Takamune, H. Saruwatari, N. Ono, Independent low-rank matrix analysis based on complex student's t-distribution for blind audio source separation. in 2017 IEEE 27th Int. Workshop Mach. Learn. Signal Process. (MLSP) (2017)

  22. N. Ono, S. Miyabe, Auxiliary-function-based independent component analysis for super-Gaussian sources, in Latent Variable Analysis and Signal Separation. ed. by V. Vigneron, V. Zarzoso, E. Moreau, R. Gribonval, E. Vincent (Springer, Berlin, Heidelberg, 2010), pp.165–172. https://doi.org/10.1007/978-3-642-15995-4_21

    Chapter  Google Scholar 

  23. N. Ono, Stable and fast update rules for independent vector analysis based on auxiliary function technique. in 2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) (pp. 189-192). IEEE (2011)

  24. A. Ozerov, C. Fevotte, Multichannel non-negative matrix factorization in convolutive mixtures for audio source separation. IEEE Trans. Audio Speech Lang. Process. 18(3), 550–563 (2010)

    Article  Google Scholar 

  25. A. Ozerov, C. Fevotte, R. Blouet, J.-L. Durrieu, Multichannel non-negative tensor factorization with structured constraints for user guided audio source separation. in 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 257-260. IEEE, (2011)

  26. Y. Sun, P. Babu, D.P. Palomar, Majorization-minimization algorithms in signal processing, communications, and machine learning. IEEE Trans. Signal Process. 65(3), 794–816 (2017)

    Article  MathSciNet  MATH  Google Scholar 

  27. H. Sawada, H. Kameoka, S. Araki, N. Ueda, Multichannel extensions of non-negative matrix factorization with complex-value. IEEE Trans. Audio Speech Lang. Process. 21(5), 971–982 (2013)

    Article  Google Scholar 

  28. H. Sawada, N. Ono, H. Kameoka, D. Kitamura, H. Saruwatari, A review of blind source separation methods: two converging routes to ILRMA originating from ICA and NMF. SIP 8(e12), 1–14 (2019)

    Google Scholar 

  29. R.S. Sutton, A.G. Barto, Reinforcement Learning: An Introduction, 2nd edn. (MIT Press, Cambridge, 2014)

    MATH  Google Scholar 

  30. R.S. Sutton, Temporal credit assignment in reinforcement learning. Doctoral Dissertation, University of Massachusetts, Amherst (1985)

  31. R.S. Sutton, Learning to predict by the methods of temporal differences. Mach. Learn. 3, 9–44 (1988)

    Article  Google Scholar 

  32. R. Scheibler, E. Bezzam, I. Dokmanić, Pyroomacoustics: A Python Package for Audio Room Simulation and Array Processing Algorithms, in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada, pp. 351–355 (2018)

  33. E. Vincent, R. Gribonval, C. Fevotte, Performance measurement in blind audio source separation. IEEE Trans. Audio Speech Lang. Process. 14(4), 1462–1469 (2006)

    Article  Google Scholar 

  34. N. Xiang, Generalization of Sabine’s reverberation theory. J. Acoust. Soc. Am. 148(3), R5–R6 (2020)

    Article  Google Scholar 

  35. A. Yvärinen, J. Karhunen, E. Oja, Independent component analysis (John Wiley & Sons, The United States of America, 2001)

    Book  Google Scholar 

  36. Y.-L. Yeh, P.-K. Yang, Design and comparison of reinforcement-learning-based time-varying PID controllers with gain-scheduled actions. Machines 9, 319 (2021)

    Article  Google Scholar 

  37. H. Zayyani, M. Babaie-Zadeh, C. Jutten, An iterative bayesian algorithm for sparse component analysis in presence of noise. IEEE Trans. Signal Process. 57(11), 4378–4390 (2009)

    Article  MathSciNet  MATH  Google Scholar 

  38. J. Zhang et al., A parallel hybrid neural network with integration of spatial and temporal features for remaining useful life prediction in prognostics. IEEE Trans. Instrum. Meas. 72, 1–12 (2023)

    Google Scholar 

  39. J. Zhang, K. Zhang, Y. An, H. Luo and S. Yin, An Integrated Multitasking Intelligent Bearing Fault Diagnosis Scheme Based on Representation Learning Under Imbalanced Sample Condition. in IEEE Transactions on Neural Networks and Learning Systems (2023)

Download references

Author information

Authors and Affiliations

  1. Department of Engineering Science and Ocean Engineering, National Taiwan University, No. 1, Sec. 4, Roosevelt Rd., Taipei, 10617, Taiwan

    Guan-Yu Chen & Chao-Nan Wang

Authors
  1. Guan-Yu Chen
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Chao-Nan Wang
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Guan-Yu Chen.

Ethics declarations

Conflict of interest

The authors declare no conflicts of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, GY., Wang, CN. Determined Blind Source Separation Combining Independent Low-rank Matrix Analysis with Optimized Parameters and Q-learning. Circuits Syst Signal Process 42, 6854–6870 (2023). https://doi.org/10.1007/s00034-023-02429-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00034-023-02429-9

Keywords