FlowTSE: Target Speaker Extraction with Flow Matching
25 points
10 months ago
| 2 comments
| arxiv.org
| HN
juancn
10 months ago
[-]
Examples can be found here: https://aiola-lab.github.io/flow-tse/
reply
max_
10 months ago
[-]
This is brilliant.

It can allow calls be be made clear when people talking in noisy places.

Assuming this can be made to work in real time.

reply