Abstract
In this paper we propose to use an instantaneous ICA method (BLUES) to separate the instruments in a real music stereo recording. We combine two strong separation techniques to segregate instruments from a mixture: ICA and binary time-frequency masking. By combining the methods, we are able to make use of the fact that the sources are differently distributed in both space, time and frequency. Our method is able to segregate an arbitrary number of instruments and the segregated sources are maintained as stereo signals. We have evaluated our method on real stereo recordings, and we can segregate instruments which are spatially different from other instruments.
This work is supported by the Danish Technical Research Council (STVF), through the framework project “Intelligent Sound”, STVF no. 26-04-0092, the PASCAL network, contract no. 506778. and the Oticon Foundation.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
- Independent Component Analysis
- Independent Component Analysis
- Blind Source Separation
- Binary Mask
- Gain Ratio
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Hyvärinen, A., Karhunen, J., Oja, E.: Independent Component Analysis. Wiley, Chichester (2001)
Casey, M., Westner, A.: Separation of mixed audio sources by independent subspace analysis. In: Proc. ICMC (2000)
Plumbley, M.D., Abdallah, S.A., Bello, J.P., Davies, M.E., Monti, G., Sandler, M.B.: Automatic music transcription and audio source separation. Cybernetics and Systems 33, 603–627 (2002)
Smaragdis, P., Casey, M.: Audio/visual independent components. In: Proc. ICA 2003, pp. 709–712 (2003)
Smaragdis, P., Brown, J.C.: Non-negative matrix factorization for polyphonic music transcription. In: Proc. WASPAA 2003, pp. 177–180 (2003)
Smaragdis, P.: Non-negative matrix factor deconvolution; extraction of multiple sound sourses from monophonic inputs. In: Puntonet, C.G., Prieto, A.G. (eds.) ICA 2004. LNCS, vol. 3195, pp. 494–499. Springer, Heidelberg (2004)
Wang, B., Plumbley, M.D.: Musical audio stream separation by non-negative matrix factorization. In: Proc. DMRN Summer Conf. (2005)
Helén, M., Virtanen, T.: Separation of drums from polyphonic music using non-negative matrix factorization and support vector machine. In: Proc. EUSIPCO 2005 (2005)
Vembu, S., Baumann, S.: Separation of vocals from polyphonic audio recordings. In: Proc. ISMIR 2005, pp. 337–344 (2005)
Wang, D.L., Brown, G.J.: Separation of speech from interfering sounds based on oscillatory correlation. IEEE Trans. Neural Networks 10, 684–697 (1999)
Bregman, A.S.: Auditory Scene Analysis, 2nd edn. MIT Press, Cambridge (1990)
Yilmaz, O., Rickard, S.: Blind separation of speech mixtures via time-frequency masking. IEEE Trans. Signal Processing 52, 1830–1847 (2004)
Roman, N., Wang, D.L., Brown, G.J.: Speech segregation based on sound localization. J. Acoust. Soc. Amer. 114, 2236–2252 (2003)
Wang, D.L.: On ideal binary mask as the computational goal of auditory scene analysis. In: Divenyi, P. (ed.) Speech Separation by Humans and Machines, pp. 181–197. Kluwer, Norwell (2005)
Jourjine, A., Rickard, S., Yilmaz, O.: Blind separation of disjoint orthogonal signals: Demixing n sources from 2 mixtures. In: Proc. ICASSP, pp. 2985–2988 (2000)
Hu, G., Wang, D.L.: Monaural speech segregation based on pitch tracking and amplitude modulation. IEEE Trans. Neural Networks 15, 1135–1150 (2004)
Kolossa, D., Orglmeister, R.: Nonlinear postprocessing for blind speech separation. In: Puntonet, C.G., Prieto, A.G. (eds.) ICA 2004. LNCS, vol. 3195, pp. 832–839. Springer, Heidelberg (2004)
Pedersen, M.S., Wang, D.L., Larsen, J., Kjems, U.: Overcomplete blind source separation by combining ICA and binary time-frequency masking. In: Proc. MLSP, pp. 15–20 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pedersen, M.S., Lehn-Schiøler, T., Larsen, J. (2006). BLUES from Music: BLind Underdetermined Extraction of Sources from Music. In: Rosca, J., Erdogmus, D., Príncipe, J.C., Haykin, S. (eds) Independent Component Analysis and Blind Signal Separation. ICA 2006. Lecture Notes in Computer Science, vol 3889. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11679363_49
Download citation
DOI: https://doi.org/10.1007/11679363_49
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-32630-4
Online ISBN: 978-3-540-32631-1
eBook Packages: Computer ScienceComputer Science (R0)