Dereverberation using joint estimation of dry speech signal and acoustic system

TL;DR

This paper proposes a novel deep learning approach for speech dereverberation that jointly estimates the dry speech signal and room impulse response, improving speech quality by addressing reverberation effects.

Contribution

It introduces a joint estimation model combining deep learning techniques for both dry speech and room impulse response, which is a new approach in dereverberation.

Findings

Joint model improves dereverberation performance

Shared parameter deep learning enhances estimation accuracy

Effective separation of dry speech and reverberation effects

Abstract

The purpose of speech dereverberation is to remove quality-degrading effects of a time-invariant impulse response filter from the signal. In this report, we describe an approach to speech dereverberation that involves joint estimation of the dry speech signal and of the room impulse response. We explore deep learning models that apply to each task separately, and how these can be combined in a joint model with shared parameters.