Papers › Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-training
Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-training
Sung-Feng Huang, Shun-Po Chuang, Da-Rong Liu, Yi-Chen Chen, Gene-Ping Yang, Hung-Yi Lee
Speech separation has been well developed, with the very successful permutation invariant training (PIT) approach, although the frequent label assignment switching happening during PIT training remains to be a problem when better convergence speed and achievable performance are desired. In this paper, we propose to perform self-supervised pre-training to stabilize the label assignment in training the speech separation model. Experiments over several types of self-supervised approaches, several typical speech separation models and two different datasets showed that very good improvements are achievable if a proper self-supervised approach is chosen.
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 | Libri2Mix | Conv-Tasnet (Libri1Mix speech enhancement pre-trained) | SDRi | 14.6 | #8 of 10 | Archive leaderboard | report |
| Speech Separation | Libri2Mix | Conv-Tasnet (Libri1Mix speech enhancement pre-trained) | SI-SDRi | 14.1 | #8 of 10 | Archive leaderboard | report |
| Speech Separation | Libri2Mix | Conv-Tasnet (Libri1Mix speech enhancement multi-task) | SDRi | 14.1 | #9 of 10 | Archive leaderboard | report |
| Speech Separation | Libri2Mix | Conv-Tasnet (Libri1Mix speech enhancement multi-task) | SI-SDRi | 13.7 | #9 of 10 | Archive leaderboard | report |
| Speech Separation | Libri2Mix | Conv-Tasnet | SDRi | 13.6 | #10 of 10 | Archive leaderboard | report |
| Speech Separation | Libri2Mix | Conv-Tasnet | SI-SDRi | 13.2 | #10 of 10 | Archive leaderboard | report |
| Speech Separation | WSJ0-2mix | DPTNet (Libri1Mix speech enhancement pre-trained) | SDRi | 21.5 | #19 of 40 | Archive leaderboard | report |
| Speech Separation | WSJ0-2mix | DPTNet (Libri1Mix speech enhancement pre-trained) | SI-SDRi | 21.3 | #19 of 40 | 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