On the Importance of Neural Wiener Filter for Resource Efficient Multichannel Speech Enhancement

TA Hsieh, J Donley, D Wong, B Xu… - ICASSP 2024-2024 …, 2024 - ieeexplore.ieee.org
We introduce a time-domain framework for efficient multichannel speech enhancement,
emphasizing low latency and computational efficiency. This framework incorporates two …

Leveraging Self-Supervised Speech Representations for Domain Adaptation in Speech Enhancement

CH Lee, C Yang, RS Srinivasa… - ICASSP 2024-2024 …, 2024 - ieeexplore.ieee.org
Deep learning based speech enhancement (SE) approaches could suffer from performance
degradation due to mismatch between training and testing environments. A realistic situation …

An MVDR-Embedded U-Net Beamformer for Effective and Robust Multichannel Speech Enhancement

CH Lee, K Patel, C Yang, Y Shen… - ICASSP 2024-2024 IEEE …, 2024 - ieeexplore.ieee.org
In multichannel speech enhancement (SE) systems, deep neural networks (DNNs) are often
utilized to directly estimate the clean speech for effective beamforming. This approach …

Reference Channel Selection by Multi-Channel Masking for End-to-End Multi-Channel Speech Enhancement

W Dai, X Li, A Politis, T Virtanen - arXiv preprint arXiv:2406.03228, 2024 - arxiv.org
In end-to-end multi-channel speech enhancement, the traditional approach of designating
one microphone signal as the reference for processing may not always yield optimal results …

Directional Gain Based Noise Covariance Matrix Estimation for MVDR Beamforming

F Zhang, C Pan, J Benesty… - ICASSP 2024-2024 IEEE …, 2024 - ieeexplore.ieee.org
This paper is devoted to the problem of noise covariance matrix (NCM) estimation. It
proposes a time-frequency masking based approach. We first present an optimal mask …