English

On the Use of Deep Mask Estimation Module for Neural Source Separation Systems

Sound 2022-06-16 v1 Audio and Speech Processing

Abstract

Most of the recent neural source separation systems rely on a masking-based pipeline where a set of multiplicative masks are estimated from and applied to a signal representation of the input mixture. The estimation of such masks, in almost all network architectures, is done by a single layer followed by an optional nonlinear activation function. However, recent literatures have investigated the use of a deep mask estimation module and observed performance improvement compared to a shallow mask estimation module. In this paper, we analyze the role of such deeper mask estimation module by connecting it to a recently proposed unsupervised source separation method, and empirically show that the deep mask estimation module is an efficient approximation of the so-called overseparation-grouping paradigm with the conventional shallow mask estimation layers.

Keywords

Cite

@article{arxiv.2206.07347,
  title  = {On the Use of Deep Mask Estimation Module for Neural Source Separation Systems},
  author = {Kai Li and Xiaolin Hu and Yi Luo},
  journal= {arXiv preprint arXiv:2206.07347},
  year   = {2022}
}

Comments

Accepted by Interspeech 2022

R2 v1 2026-06-24T11:51:56.557Z