Sparsity and low-rank amplitude based blind source separation

F Feng, M Kowalski - 2017 IEEE International Conference on …, 2017 - ieeexplore.ieee.org
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017ieeexplore.ieee.org
This paper presents a new method for blind source separation problem in reverberant
environments with more sources than microphones. Based on the sparsity property in the
time-frequency domain and the low-rank assumption of the spectrogram of the source, the
STRAUSS (SparsiTy and low-Rank AmplitUde based Source Separation) method is
developed. Numerical evaluations show that the proposed method outperforms the existing
multichannel NMF approaches, while it is exclusively based on amplitude information.
This paper presents a new method for blind source separation problem in reverberant environments with more sources than microphones. Based on the sparsity property in the time-frequency domain and the low-rank assumption of the spectrogram of the source, the STRAUSS (SparsiTy and low-Rank AmplitUde based Source Separation) method is developed. Numerical evaluations show that the proposed method outperforms the existing multichannel NMF approaches, while it is exclusively based on amplitude information.
ieeexplore.ieee.org
Showing the best result for this search. See all results