Attention-Driven Multichannel Speech Enhancement in Moving Sound Source Scenarios

[Free GPT-4]
[PDF] arxiv.org

Multichannel long-term streaming neural speech enhancement for static and moving speakers

C Quan, X Li - arxiv preprint arxiv:2403.07675, 2024 - arxiv.org
In this work, we extend our previously proposed offline SpatialNet for long-term streaming
multichannel speech enhancement in both static and moving speaker scenarios. SpatialNet …
Save Cite Cited by 19 Related articles All 2 versionsFree GPT-4 View as HTML
[Free GPT-4]
[PDF] arxiv.org

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 …
Save Cite Related articles All 2 versionsFree GPT-4 View as HTML
[Free GPT-4]
[PDF] arxiv.org

Array Geometry-Robust Attention-Based Neural Beamformer for Moving Speakers

M Tammen, T Ochiai, M Delcroix, T Nakatani… - arxiv preprint arxiv …, 2024 - arxiv.org
Recently, a mask-based beamformer with attention-based spatial covariance matrix
aggregator (ASA) was proposed, which was demonstrated to track moving sources …
Save Cite Related articles All 2 versionsFree GPT-4 View as HTML