Reverberant Audio Source Separation via Sparse and Low-Rank Modeling
This work addresses audio source separation for reverberant music mixtures, representing an incremental improvement over existing methods.
The paper tackled the problem of audio source separation from underdetermined convolutive mixtures by incorporating a low-rank prior on source spectrograms, resulting in an algorithm that improves state-of-the-art methods by over 2 dB in signal-to-distortion ratio.
The performance of audio source separation from underdetermined convolutive mixture assuming known mixing filters can be significantly improved by using an analysis sparse prior optimized by a reweighting l1 scheme and a wideband datafidelity term, as demonstrated by a recent article. In this letter, we show that the performance can be improved even more significantly by exploiting a low-rank prior on the source spectrograms.We present a new algorithm to estimate the sources based on i) an analysis sparse prior, ii) a reweighting scheme so as to increase the sparsity, iii) a wideband data-fidelity term in a constrained form, and iv) a low-rank constraint on the source spectrograms. Evaluation on reverberant music mixtures shows that the resulting algorithm improves state-of-the-art methods by more than 2 dB of signal-to-distortion ratio.