Skip to main content
SpringerLink
Log in
Book cover

Conference on Complex, Intelligent, and Software Intensive Systems

CISIS 2019: Complex, Intelligent, and Software Intensive Systems pp 743–751Cite as

Automatic Determination of the Optimum Number of Updates in Synchronized Joint Diagonalization

  • Conference paper
  • First Online:

  • 1651 Accesses

Part of the book series: Advances in Intelligent Systems and Computing ((AISC,volume 993))

Abstract

This study focuses on Synchronized Joint Diagonalization (SJD), which is a newly proposed sound source separation (BSS) method. SJD performs iterative updates of parameters for source separation. For its practical use, it is necessary to determine the optimum number of the iterations. We proposed to optimize it by observing the differences of the estimated activation matrix before and after updates during each iteration. We confirmed the effectiveness of this approach by BSS experiments.

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

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   169.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   219.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

References

  1. Lee, T.-W.: Independent Component Analysis-Theory and Applications. Kluwer, Norwell (1998)

    Book  Google Scholar 

  2. Lee, I., et al.: Fast fixedpoint independent vector analysis algorithms for convolutive blind source separation. Sig. Process. 87(8), 1859–1871 (2007)

    Google Scholar 

  3. Lee, D.D., et al.: Learning the parts of objects with nonnegative matrix factorization. Nature 401, 788–791 (1999)

    Article  Google Scholar 

  4. Sawada, H., et al.: Multichannel extensions of non-negative matrix factorization with complex-valued data. IEEE Trans. ASLP 21(5), 971–982 (2013)

    Google Scholar 

  5. Kitamura, D., et al.: Dtermined blind source separation unifying independent vector analysis and nennegative matrix factorization. IEEE/ACM Trans. Audio Speech Lang. Process. 24(9), 1626–1641 (2016)

    Article  Google Scholar 

  6. Sawada, H.: Blind signal separation by synchronized joint diagonalization. In: 32nd SIP Symposium, pp. 332–337 (2017)

    Google Scholar 

  7. Ziehe, A., et al.: A fast algorithm for joint diagonalization with non-orthogonal transformations and its application to blind source separation. J. Mach. Learn. Res. 5, 777–800 (2004)

    Google Scholar 

  8. Araki, S., et al.: The 2011 signal separation evaluation campaign (SiSEC2011): -audio source separation. In: Latent Variable Analysis and Signal Separation, pp. 414–422. Springer, Berlin (2012)

    Google Scholar 

  9. RWCP: Sound Scene Database in Real Acoustic Enviroment (RWCP-SSD), Speech Resources Consortium. http://research.nii.ac.jp/src/RWCP-SSD.html. Accessed 21 Aug 2018

  10. Vincent, E., et al.: First stereo audio source separation evaluation campaign: data algorithm and results. In: Independent Component Analysis and Signal Separation, pp. 552–559. Springer, Berlin (2007)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Graduate School of Engineering, Oita University, 700, Dannoharu, Oita-shi, Oita, Japan

    Taiki Izumi

  2. Denso IT Laboratory, Shibuya cross tower 28F, Shibuya-ku, Tokyo, Japan

    Yuuki Tachioka

  3. Faculty of Engineering, Oita University, 700, Dannoharu, Oita-shi, Oita, Japan

    Shingo Uenohara & Ken’ichi Furuya

Authors
  1. Taiki Izumi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yuuki Tachioka
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Shingo Uenohara
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ken’ichi Furuya
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Taiki Izumi .

Editor information

Editors and Affiliations

  1. Department of Information and Communication Engineering, Fukuoka Institute of Technology, Faculty of Information Engineering, Fukuoka, Japan

    Leonard Barolli

  2. School of Software, University of Technology Sydney (UTS), Ultimo, NSW, Australia

    Farookh Khadeer Hussain

  3. Department of Information and Communication Engineering, Fukuoka Institute of Technology, Faculty of Information Engineering, Fukuoka, Japan

    Makoto Ikeda

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Izumi, T., Tachioka, Y., Uenohara, S., Furuya, K. (2020). Automatic Determination of the Optimum Number of Updates in Synchronized Joint Diagonalization. In: Barolli, L., Hussain, F., Ikeda, M. (eds) Complex, Intelligent, and Software Intensive Systems. CISIS 2019. Advances in Intelligent Systems and Computing, vol 993. Springer, Cham. https://doi.org/10.1007/978-3-030-22354-0_67

Download citation

Publish with us

Policies and ethics

Search

Navigation