FlowTSE: Target Speaker Extraction with Flow Matching

by agold97 on 5/28/2025, 2:30:33 PM with 2 comments

  • by juancn on 5/28/2025, 5:03:13 PM

    Examples can be found here: https://aiola-lab.github.io/flow-tse/

  • by max_ on 5/28/2025, 5:15:21 PM

    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.