Receptive Field Analysis of Temporal Convolutional Networks for Monaural Speech Dereverberation

TL;DR

This paper investigates how the receptive field size of temporal convolutional networks affects their ability to dereverberate monaural speech, showing larger RFs improve performance especially with longer reverberation times.

Contribution

It provides a detailed analysis of the impact of receptive field size on TCN performance in speech dereverberation, filling a gap in existing research.

Findings

Larger RF improves dereverberation performance for smaller TCN models.

Wider RF benefits dereverberation of speech with longer reverberation times.

Performance gains are significant with increased RF in various reverberation scenarios.

Abstract

Speech dereverberation is often an important requirement in robust speech processing tasks. Supervised deep learning (DL) models give state-of-the-art performance for single-channel speech dereverberation. Temporal convolutional networks (TCNs) are commonly used for sequence modelling in speech enhancement tasks. A feature of TCNs is that they have a receptive field (RF) dependent on the specific model configuration which determines the number of input frames that can be observed to produce an individual output frame. It has been shown that TCNs are capable of performing dereverberation of simulated speech data, however a thorough analysis, especially with focus on the RF is yet lacking in the literature. This paper analyses dereverberation performance depending on the model size and the RF of TCNs. Experiments using the WHAMR corpus which is extended to include room impulse responses (RIRs) with larger T60 values demonstrate that a larger RF can have significant improvement in performance when training smaller TCN models. It is also demonstrated that TCNs benefit from a wider RF when dereverberating RIRs with larger RT60 values.