Abstract
We propose a semi-blind method for separation of stereo recordings of several sources. The method begins with computation of a set of cancellation filters for potential fixed positions of the sources. These filters are computed from one-source-only intervals selected upon cross-talk detection. Each source in some of the fixed positions is canceled by the corresponding filter, by which the other sources are separated. The former source can be then separated by adaptive suppression of the separated sources. To select the appropriate cancellation filter, we use Independent Component Analysis. The performance of the proposed method is verified on real-world SiSEC data with two fixed and/or moving sources.
This work was supported by Grant Agency of the Czech Republic through the project P103/11/1947.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Benesty, J., Makino, S., Chen, J. (eds.): Speech Enhancement, 1st edn. Springer, Heidelberg (2005)
Li, J., Sakamoto, S., Hongo, S., Akagi, M., Suzuki, Y.: Two-stage binaural speech enhancement with Wiener filter based on equalization-cancellation model. In: Proc. of WASPAA 2009, New Paltz, New York, pp. 133–136 (October 2009)
Koldovský, Z., Tichavský, P.: Time-Domain Blind Separation of Audio Sources on the basis of a Complete ICA Decomposition of an Observation Space. IEEE Trans. on Speech, Audio and Language Processing 19(2), 406–416 (2011)
Koldovský, Z., Tichavský, P., Málek, J.: A Semi-Blind Noise Extraction Using Partially Known Position of the Target Source. Submitted to a Conference (2011)
Albouy, B., Deville, Y.: Alternative structures and power spectrum criteria for blind segmentation and separation of convolutive speech mixtures. In: Proc. of ICA 2003, Nara, Japan, April 1-4, pp. 361–366 (2003)
Tichavský, P., Yeredor, A.: Fast Approximate Joint Diagonalization Incorporating Weight Matrices. IEEE Trans. on Signal Processing 57(3), 878–891 (2009)
Sundaram, N., et al.: Usable speech detection using linear predictive analysis - a model based approach. In: Proc. of ISPACS, Awaji Island, Japan, pp. 231–235 (2003)
Koldovský, Z., Nouza, J., Kolorenč, J.: Continuous Time-Frequency Masking Method for Blind Speech Separation with Adaptive Choice of Threshold Parameter Using ICA. In: Proc. of Interspeech 2006, Pittsburgh PA, USA, September 17-21, pp. 2578–2581 (2006)
Févotte, C., Gribonval, R., Vincent, E.: BSS EVAL toolbox user guide. IRISA, Rennes, France, Tech. Rep. 1706 (2005), http://www.irisa.fr/metiss/bss_eval
Rutkowski, T.M., et al.: Identification and tracking of active speaker’s position in noisy environments. In: Proc. of IWAENC 2003, Kyoto, Japan, pp. 283–286 (2003)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Málek, J., Koldovský, Z., Tichavský, P. (2012). Semi-blind Source Separation Based on ICA and Overlapped Speech Detection. In: Theis, F., Cichocki, A., Yeredor, A., Zibulevsky, M. (eds) Latent Variable Analysis and Signal Separation. LVA/ICA 2012. Lecture Notes in Computer Science, vol 7191. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-28551-6_57
Download citation
DOI: https://doi.org/10.1007/978-3-642-28551-6_57
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-28550-9
Online ISBN: 978-3-642-28551-6
eBook Packages: Computer ScienceComputer Science (R0)