TPARN: Triple-path Attentive Recurrent Network for Time-domain Multichannel Speech Enhancement

TL;DR

This paper introduces TPARN, a novel multichannel speech enhancement model that extends dual-path RNNs with a third spatial path, achieving superior performance in time-domain speech enhancement.

Contribution

The paper proposes TPARN, a triple-path attentive recurrent network that incorporates spatial context for multichannel speech enhancement, extending existing dual-path models with an additional spatial dimension.

Findings

TPARN outperforms existing state-of-the-art methods.

TPARN effectively captures spatial and temporal information.

Experimental results validate the superiority of TPARN.

Abstract

In this work, we propose a new model called triple-path attentive recurrent network (TPARN) for multichannel speech enhancement in the time domain. TPARN extends a single-channel dual-path network to a multichannel network by adding a third path along the spatial dimension. First, TPARN processes speech signals from all channels independently using a dual-path attentive recurrent network (ARN), which is a recurrent neural network (RNN) augmented with self-attention. Next, an ARN is introduced along the spatial dimension for spatial context aggregation. TPARN is designed as a multiple-input and multiple-output architecture to enhance all input channels simultaneously. Experimental results demonstrate the superiority of TPARN over existing state-of-the-art approaches.