The PCG-AIID System for L3DAS22 Challenge: MIMO and MISO convolutional recurrent Network for Multi Channel Speech Enhancement and Speech Recognition

TL;DR

This paper presents a two-stage multi-channel speech enhancement system using MIMO and MISO convolutional recurrent networks, achieving top performance in the L3DAS22 challenge for reverberant office environments.

Contribution

The paper introduces a novel two-stage framework combining MIMO and MISO networks for improved multi-channel speech denoising and dereverberation in challenging environments.

Findings

Ranked 3rd in L3DAS22 challenge

Achieved 3.2% WER on test set

Attained 0.972 STOI score

Abstract

This paper described the PCG-AIID system for L3DAS22 challenge in Task 1: 3D speech enhancement in office reverberant environment. We proposed a two-stage framework to address multi-channel speech denoising and dereverberation. In the first stage, a multiple input and multiple output (MIMO) network is applied to remove background noise while maintaining the spatial characteristics of multi-channel signals. In the second stage, a multiple input and single output (MISO) network is applied to enhance the speech from desired direction and post-filtering. As a result, our system ranked 3rd place in ICASSP2022 L3DAS22 challenge and significantly outperforms the baseline system, while achieving 3.2% WER and 0.972 STOI on the blind test-set.