Papers › Many-Speakers Single Channel Speech Separation with Optimal Permutation Training
Many-Speakers Single Channel Speech Separation with Optimal Permutation Training
Shaked Dovrat, Eliya Nachmani, Lior Wolf
Single channel speech separation has experienced great progress in the last few years. However, training neural speech separation for a large number of speakers (e.g., more than 10 speakers) is out of reach for the current methods, which rely on the Permutation Invariant Loss (PIT). In this work, we present a permutation invariant training that employs the Hungarian algorithm in order to train with an O(C³) time complexity, where C is the number of speakers, in comparison to O(C!) of PIT based methods. Furthermore, we present a modified architecture that can handle the increased number of speakers. Our approach separates up to $20$ speakers and improves the previous results for large C by a wide margin.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Speech Separation | Libri10Mix | Hungarian PIT | SI-SDRi | 7.78 | #3 of 3 | Archive leaderboard | report |
| Speech Separation | Libri15Mix | Hungarian PIT | SI-SDRi | 5.66 | #1 of 1 | Archive leaderboard | report |
| Speech Separation | Libri20Mix | Hungarian PIT | SI-SDRi | 4.26 | #2 of 2 | Archive leaderboard | report |
| Speech Separation | Libri5Mix | Hungarian PIT | SI-SDRi | 12.72 | #4 of 4 | Archive leaderboard | report |
| Speech Separation | WSJ0-5mix | Hungarian PIT | SI-SDRi | 13.22 | #2 of 6 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections