English

Task splitting for DNN-based acoustic echo and noise removal

Audio and Speech Processing 2022-07-14 v2 Sound

Abstract

Neural networks have led to tremendous performance gains for single-task speech enhancement, such as noise suppression and acoustic echo cancellation (AEC). In this work, we evaluate whether it is more useful to use a single joint or separate modules to tackle these problems. We describe different possible implementations and give insights into their performance and efficiency. We show that using a separate echo cancellation module and a module for noise and residual echo removal results in less near-end speech distortion and better performance during double-talk at same complexity.

Keywords

Cite

@article{arxiv.2205.06931,
  title  = {Task splitting for DNN-based acoustic echo and noise removal},
  author = {Sebastian Braun and Maria Luis Valero},
  journal= {arXiv preprint arXiv:2205.06931},
  year   = {2022}
}

Comments

to appear in IEEE IWAENC 2022

R2 v1 2026-06-24T11:17:06.098Z