FlowTSE: Target Speaker Extraction with Flow Matching Posted by agold97 on Wednesday May 28, 2025 @10:30AM from the arxiv.org dept. https://arxiv.org/abs/2505.14465 ( 2 comments | 5 points | on HN )
It can allow calls be be made clear when people talking in noisy places.
Assuming this can be made to work in real time.