ASSDSPMay 20, 2020

Consistent ICA: Determined BSS meets spectrogram consistency

arXiv:2005.09873v114 citations
AI Analysis

This work addresses a specific issue in audio processing for researchers and practitioners, presenting an incremental improvement by applying spectrogram consistency to an existing bottleneck.

The paper tackled the permutation problem in determined blind source separation by leveraging spectrogram consistency, resulting in a method that aligns frequency-wise filters to correctly assign separated components to their sources.

Multichannel audio blind source separation (BSS) in the determined situation (the number of microphones is equal to that of the sources), or determined BSS, is performed by multichannel linear filtering in the time-frequency domain to handle the convolutive mixing process. Ordinarily, the filter treats each frequency independently, which causes the well-known permutation problem, i.e., the problem of how to align the frequency-wise filters so that each separated component is correctly assigned to the corresponding sources. In this paper, it is shown that the general property of the time-frequency-domain representation called spectrogram consistency can be an assistant for solving the permutation problem.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes