Adapting Speech Separation to Real-World Meetings Using Mixture Invariant Training — mentioned by kajecounterhack

Thu, 16 Mar 2023 17:19:51 GMT

https://arxiv.org/abs/2110.10739 I haven't seen it provided as a commercial service or free model yet, but there is open source code for Mixit that lets you train using the open source / canned FUSS dataset.

Paper and discussion history. A mention is not an endorsement.

Adapting Speech Separation to Real-World Meetings Using Mixture Invariant Training · HackerPapers discussions

Adapting Speech Separation to Real-World Meetings Using Mixture Invariant Training — mentioned by kajecounterhack