Controllable Multichannel Speech Dereverberation based on Deep Neural Networks

TL;DR

This paper introduces a controllable multichannel speech dereverberation method using deep neural networks, allowing adjustable dereverberation levels by a simple control parameter, and demonstrates its effectiveness in various simulated environments.

Contribution

It presents a novel neural network approach with a controllable dereverberation level, addressing limitations of previous methods that only recover direct sound and early reflections.

Findings

Effective dereverberation in simulated environments

Controllable dereverberation levels demonstrated

Improved speech quality with adjustable dereverberation

Abstract

Neural network based speech dereverberation has achieved promising results in recent studies. Nevertheless, many are focused on recovery of only the direct path sound and early reflections, which could be beneficial to speech perception, are discarded. The performance of a model trained to recover clean speech degrades when evaluated on early reverberation targets, and vice versa. This paper proposes a novel deep neural network based multichannel speech dereverberation algorithm, in which the dereverberation level is controllable. This is realized by adding a simple floating-point number as target controller of the model. Experiments are conducted using spatially distributed microphones, and the efficacy of the proposed algorithm is confirmed in various simulated conditions.