The PCG-AIID System for L3DAS22 Challenge: MIMO and MISO convolutional recurrent Network for Multi Channel Speech Enhancement and Speech Recognition
This work addresses speech enhancement for noisy, reverberant environments, which is incremental as it builds on existing challenge frameworks.
The paper tackled multi-channel speech enhancement in a reverberant office environment by proposing a two-stage MIMO and MISO convolutional recurrent network, achieving 3rd place in the L3DAS22 challenge with 3.2% WER and 0.972 STOI on the blind test-set.
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.