English

A Time-domain Monaural Speech Enhancement with Feedback Learning

Sound 2020-11-06 v3 Audio and Speech Processing

Abstract

In this paper, we propose a type of neural network with feedback learning in the time domain called FTNet for monaural speech enhancement, where the proposed network consists of three principal components. The first part is called stage recurrent neural network, which is introduced to effectively aggregate the deep feature dependencies across different stages with a memory mechanism and also remove the interference stage by stage. The second part is the convolutional auto-encoder. The third part consists of a series of concatenated gated linear units, which are capable of facilitating the information flow and gradually increasing the receptive fields. Feedback learning is adopted to improve the parameter efficiency and therefore, the number of trainable parameters is effectively reduced without sacrificing its performance. Numerous experiments are conducted on TIMIT corpus and experimental results demonstrate that the proposed network can achieve consistently better performance in terms of both PESQ and STOI scores than two state-of-the-art time domain-based baselines in different conditions.

Keywords

Cite

@article{arxiv.2003.09815,
  title  = {A Time-domain Monaural Speech Enhancement with Feedback Learning},
  author = {Andong Li and Chengshi Zheng and Linjuan Cheng and Renhua Peng and Xiaodong Li},
  journal= {arXiv preprint arXiv:2003.09815},
  year   = {2020}
}

Comments

Accepted by APSIPA 2020

R2 v1 2026-06-23T14:22:54.972Z