Low complexity blind separation technique to solve the permutation ambiguity of convolutive speech mixtures

Lima PF, Miranda RK, Da Costa JPC, Zelenovsky R, Yuan Y, Del Galdo G (2016)

Publication Type: Conference contribution

Publication year: 2016

Publisher: Institute of Electrical and Electronics Engineers Inc.

Conference Proceedings Title: 2016, 10th International Conference on Signal Processing and Communication Systems, ICSPCS 2016 - Proceedings

Event location: Surfers Paradise, QLD, AUS

ISBN: 9781509009411

DOI: 10.1109/ICSPCS.2016.7843325

Abstract

Microphone arrays can be incorporated in several devices ranging from hearing aids and bioacoustic recording equipment to teleconference phones and forensic sound recorders in order to attenuate the interference of unwanted sounds. The separation of speech mixtures can be easily performed on the frequency domain independently for each frequency component. However, in order to combine the separated signals of each frequency component, the permutation ambiguity should be solved. The state-of-the-art technique relies on an iterative computation of the dispersions of the differences between the source profiles. In this paper, we propose a low complexity solution for the permutation ambiguity with similar accuracy based on one dispersion.

Involved external institutions

Universidade de Brasília BR Brazil (BR) Freie Universität Berlin DE Germany (DE) Technische Universität Ilmenau DE Germany (DE)

How to cite

APA:

Lima, P.F., Miranda, R.K., Da Costa, J.P.C., Zelenovsky, R., Yuan, Y., & Del Galdo, G. (2016). Low complexity blind separation technique to solve the permutation ambiguity of convolutive speech mixtures. In Tadeusz A Wysocki, Beata J Wysocki (Eds.), 2016, 10th International Conference on Signal Processing and Communication Systems, ICSPCS 2016 - Proceedings. Surfers Paradise, QLD, AUS: Institute of Electrical and Electronics Engineers Inc..

MLA:

Lima, Pedro F.C., et al. "Low complexity blind separation technique to solve the permutation ambiguity of convolutive speech mixtures." Proceedings of the 10th International Conference on Signal Processing and Communication Systems, ICSPCS 2016, Surfers Paradise, QLD, AUS Ed. Tadeusz A Wysocki, Beata J Wysocki, Institute of Electrical and Electronics Engineers Inc., 2016.

BibTeX: Download