Multiple Instrument Mixtures Source Separation Evaluation Using Instrument-Dependent NMF Models

  • Francisco J. Rodriguez-Serrano
  • Julio J. Carabias-Orti
  • Pedro Vera-Candeas
  • Tuomas Virtanen
  • Nicolas Ruiz-Reyes
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7191)

Abstract

This work makes use of instrument-dependent models to separate the different sources of multiple instrument mixtures. Three different models are applied: (a) basic spectral model with harmonic constraint, (b) source-filter model with harmonic-comb excitation and (c) source-filter model with multi-excitation per instrument. The parameters of the models are optimized by an augmented NMF algorithm and learnt in a training stage. The models are presented in [1], here the experimental setting for the application to source separation is explained. The instrument-dependent NMF models are first trained and then a test stage is performed. A comparison with other state-of-the-art software is presented. Results show that source-filter model with multi-excitation per instrument outperforms the other compared models.

Keywords

non-negative matrix factorization (NMF) source-filter model excitation modeling spectral analysis music source separation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Carabias-Orti, J.J., Virtanen, T., Vera-Candeas, P., Ruiz-Reyes, N., Canadas-Quesada, F.J.: Musical Instrument Sound Multi-Excitation Model for Non-Negative Spectrogram Factorization. IEEE Journal on Selected Topics on Signal Processing 5(6), 1144–1158 (2011)CrossRefGoogle Scholar
  2. 2.
    Virtanen, T., Klapuri, A.: Analysis of polyphonic audio using source-filter model and non-negative matrix factorization. In: Advances in Models for Acoustic Processing, Neural Information Processing Systems Workshop (2006)Google Scholar
  3. 3.
    Heittola, T., Klapuri, A., Virtanen, T.: Musical instrument recognition in polyphonic audio using source-filter model for sound separation. In: Proc. 10th Int. Society for Music Information Retrieval Conf. (ISMIR), Kobe, Japan (2009)Google Scholar
  4. 4.
    Virtanen, T.: Monaural sound source separation by nonnegative matrix factorization with temporal continuity and sparseness criteria. IEEE Transactions on Audio, Speech, and Language Processing 15(3), 1066–1074 (2007)CrossRefGoogle Scholar
  5. 5.
    Goto, M.: Development of the RWC Music Database. In: Proc. of the 18th International Congress on Acoustics (ICA 2004), pp.I-553–I-556 (April 2004) (invited paper)Google Scholar
  6. 6.
    Mirex 2007: Music information retrieval evaluation exchange, http://www.music-ir.org/mirex/wiki/2007:MIREX_HOME
  7. 7.
    Vincent, E., Bertin, N., Badeau, R.: Adaptive Harmonic Spectral Decomposition for Multiple Pitch Estimation. IEEE Transactions on Audio, Speech, and Language Processing 18(3), 528–537 (2010)CrossRefGoogle Scholar
  8. 8.
    Ruiz-Reyes, N., Vera-Candeas, P.: Adaptive Signal Modeling Based on Sparse Approximations for Scalable Parametric Audio Coding. IEEE Transactions on Audio, Speech, and Language Processing 18(3), 447–460 (2010)CrossRefGoogle Scholar
  9. 9.
    Every, M.R., Szymanski, J.E.: Separation of synchronous pitched notes by spectral filtering of harmonics. IEEE Trans. Audio, Speech, Lang. Process. 14(5), 1845–1856 (2006)CrossRefGoogle Scholar
  10. 10.
    Ozerov, A., Vincent, E.: A general flexible framework for the handling of prior information in audio source separation. IEEE Trans. Audio, Speech, Lang. Process (to appear)Google Scholar
  11. 11.
    Vincent, E.: Musical source separation using time-frequency source priors. IEEE Transactions on Audio, Speech, and Language Processing 14(1), 91–98 (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Francisco J. Rodriguez-Serrano
    • 1
  • Julio J. Carabias-Orti
    • 1
  • Pedro Vera-Candeas
    • 1
  • Tuomas Virtanen
    • 2
  • Nicolas Ruiz-Reyes
    • 1
  1. 1.Universidad de JaenJaenSpain
  2. 2.Tampere University of TechnologyTampereFinland

Personalised recommendations