Improving Dual-Microphone Speech Enhancement by Learning Cross-Channel Features with Multi-Head Attention

TL;DR

This paper introduces a novel dual-microphone speech enhancement model using multi-head cross-attention to better learn cross-channel features, combined with a multi-task SNR estimator and spectral gain for improved noise suppression.

Contribution

The paper proposes a new MHCA-CRN architecture that effectively learns cross-channel features and incorporates a multi-task SNR estimator to reduce speech distortion in dual-microphone speech enhancement.

Findings

Outperforms several state-of-the-art models in speech enhancement tasks.

Effectively learns mutual relationships between spatial and spectral features.

Reduces residual noise and speech distortion.

Abstract

Hand-crafted spatial features, such as inter-channel intensity difference (IID) and inter-channel phase difference (IPD), play a fundamental role in recent deep learning based dual-microphone speech enhancement (DMSE) systems. However, learning the mutual relationship between artificially designed spatial and spectral features is hard in the end-to-end DMSE. In this work, a novel architecture for DMSE using a multi-head cross-attention based convolutional recurrent network (MHCA-CRN) is presented. The proposed MHCA-CRN model includes a channel-wise encoding structure for preserving intra-channel features and a multi-head cross-attention mechanism for fully exploiting cross-channel features. In addition, the proposed approach specifically formulates the decoder with an extra SNR estimator to estimate frame-level SNR under a multi-task learning framework, which is expected to avoid speech distortion led by end-to-end DMSE module. Finally, a spectral gain function is adopted to further suppress the unnatural residual noise. Experiment results demonstrated superior performance of the proposed model against several state-of-the-art models.