Late Reverberation Suppression Using Recurrent Neural Networks with Long Short-Term Memory

Yan Zhao; DeLiang Wang; Buye Xu; Tao Zhang

ICASSP 2018accepted0 citations

Late Reverberation Suppression Using Recurrent Neural Networks with Long Short-Term Memory

Yan Zhao, DeLiang Wang, Buye Xu, Tao Zhang

Abstract

Human speech is usually distorted by room reverberation. These corruptions degrade speech quality and intelligibility, especially under a long reverberation time, and they also pose a serious problem for many speech-related applications such as automatic speech recognition. In this paper, we propose a supervised speech dereverberation algorithm that models late reverberation using a recurrent neural network (RNN) with long short-term memory (LSTM). By taking advantage of LSTM's ability to capture a long history, late reverberation can be effectively removed by the proposed approach. Systematic evaluations indicate that our approach improves the quality of reverberant speech in a wide range of reverberant conditions. Moreover, the proposed system is a causal system, which can be applied in real-time applications.

BibTeX

@inproceedings{icassp2018_latereverberatio,
  title = {Late Reverberation Suppression Using Recurrent Neural Networks with Long Short-Term Memory},
  author = {Yan Zhao and DeLiang Wang and Buye Xu and Tao Zhang},
  booktitle = {ICASSP 2018},
  year = {2018}
}