English

Incorporating Multi-Target in Multi-Stage Speech Enhancement Model for Better Generalization

Audio and Speech Processing 2021-07-12 v1

Abstract

Recent single-channel speech enhancement methods based on deep neural networks (DNNs) have achieved remarkable results, but there are still generalization problems in real scenes. Like other data-driven methods, DNN-based speech enhancement models produce significant performance degradation on untrained data. In this study, we make full use of the contribution of multi-target joint learning to the model generalization capability, and propose a lightweight and low-computing dilated convolutional network (DCN) model for a more robust speech denoising task. Our goal is to integrate the masking target, the mapping target, and the parameters of the traditional speech enhancement estimator into a DCN model to maximize their complementary advantages. To do this, we build a multi-stage learning framework to deal with multiple targets in stages to achieve their joint learning, namely `MT-in-MS'. Our experimental results show that compared with the state-of-the-art time domain and time-frequency domain models, this proposed low-cost DCN model can achieve better generalization performance in speaker, noise, and channel mismatch cases.

Keywords

Cite

@article{arxiv.2107.04232,
  title  = {Incorporating Multi-Target in Multi-Stage Speech Enhancement Model for Better Generalization},
  author = {Lu Zhang and Mingjiang Wang and Andong Li and Zehua Zhang and Xuyi Zhuang},
  journal= {arXiv preprint arXiv:2107.04232},
  year   = {2021}
}

Comments

Submitted to APSIPA-ASC 2021

R2 v1 2026-06-24T04:01:49.175Z