English

A Multi-Stage Triple-Path Method for Speech Separation in Noisy and Reverberant Environments

Sound 2023-03-08 v1 Machine Learning Audio and Speech Processing

Abstract

In noisy and reverberant environments, the performance of deep learning-based speech separation methods drops dramatically because previous methods are not designed and optimized for such situations. To address this issue, we propose a multi-stage end-to-end learning method that decouples the difficult speech separation problem in noisy and reverberant environments into three sub-problems: speech denoising, separation, and de-reverberation. The probability and speed of searching for the optimal solution of the speech separation model are improved by reducing the solution space. Moreover, since the channel information of the audio sequence in the time domain is crucial for speech separation, we propose a triple-path structure capable of modeling the channel dimension of audio sequences. Experimental results show that the proposed multi-stage triple-path method can improve the performance of speech separation models at the cost of little model parameter increment.

Keywords

Cite

@article{arxiv.2303.03732,
  title  = {A Multi-Stage Triple-Path Method for Speech Separation in Noisy and Reverberant Environments},
  author = {Zhaoxi Mu and Xinyu Yang and Xiangyuan Yang and Wenjing Zhu},
  journal= {arXiv preprint arXiv:2303.03732},
  year   = {2023}
}

Comments

Accepted by ICASSP 2023

R2 v1 2026-06-28T09:05:04.759Z