LGMLAug 24, 2018

Multi-scenario deep learning for multi-speaker source separation

arXiv:1808.08095v12 citations
AI Analysis

This addresses the limitation of existing methods being restricted to specific speaker counts, offering a more flexible solution for audio processing applications.

The paper tackled the problem of multi-speaker source separation across different numbers of speakers, showing that data from one scenario helps another and that a single model trained on multiple scenarios can match the performance of scenario-specific models.

Research in deep learning for multi-speaker source separation has received a boost in the last years. However, most studies are restricted to mixtures of a specific number of speakers, called a specific scenario. While some works included experiments for different scenarios, research towards combining data of different scenarios or creating a single model for multiple scenarios have been very rare. In this work it is shown that data of a specific scenario is relevant for solving another scenario. Furthermore, it is concluded that a single model, trained on different scenarios is capable of matching performance of scenario specific models.

Code Implementations1 repo
Foundations

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

Your Notes