Reference : Multichannel Source Separation Using Time-Deconvolutive CNMF
Scientific journals : Article
Engineering, computing & technology : Electrical & electronics engineering
Security, Reliability and Trust
Multichannel Source Separation Using Time-Deconvolutive CNMF
Dias, Thadeu mailto [Federal University of Rio de Janeiro (UFRJ)]
Alves Martins, Wallace mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
Biscainho, Luiz Wagner mailto [Federal University of Rio de Janeiro (UFRJ)]
Journal of Communication and Information Systems
[en] Blind source separation ; convolutive mixture ; NMF ; deconvolutive NMF
[en] This paper addresses the separation of audio sources from convolutive mixtures captured by a microphone array. We approach the problem using complex-valued non-negative matrix factorization (CNMF), and extend previous works by tailoring advanced (single-channel) NMF models, such as the deconvolutive NMF, to the multichannel factorization setup. Further, a sparsity-promoting scheme is proposed so that the underlying estimated parameters better fit the time-frequency properties inherent in some audio sources. The proposed parameter estimation framework is compatible with previous related works, and can be thought of as a step toward a more general method. We evaluate the resulting separation accuracy using a simulated acoustic scenario, and the tests confirm that the proposed algorithm provides superior separation quality when compared to a state-of-the-art benchmark. Finally, an analysis of the effects of the introduced regularization term shows that the solution is in fact steered toward a sparser representation.
Interdisciplinary Centre for Security, Reliability and Trust (SnT) > SIGCOM

File(s) associated to this reference

Fulltext file(s):

Open access
707-Article Text-3075-1-10-20200514.pdfPublisher postprint1.57 MBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.