TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Speech/Speech Separation/Libri2Mix

Speech Separation on Libri2Mix

Metric: SI-SDRi (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕SI-SDRi▼Extra DataPaperDate↕Code
1MossFormer2 (w speed perturb)22.2No--Code
2TF-Locoformer (M)22.1NoTF-Locoformer: Transformer with Local Modeling b...2024-08-06Code
3MossFormer2 (w/o DM)21.7No--Code
4Separate And Diffuse21.5NoSeparate And Diffuse: Using a Pretrained Diffusi...2023-01-25-
5WHYV17.5NoWanna hear your voice? A sample is all we need!2024-10-01-
6TDANet Large17.4NoAn efficient encoder-decoder architecture with t...2022-09-30Code
7TDANet16.9NoAn efficient encoder-decoder architecture with t...2022-09-30Code
8Conv-Tasnet (Libri1Mix speech enhancement pre-trained)14.1YesStabilizing Label Assignment for Speech Separati...2020-10-29Code
9Conv-Tasnet (Libri1Mix speech enhancement multi-task)13.7YesStabilizing Label Assignment for Speech Separati...2020-10-29Code
10Conv-Tasnet13.2NoStabilizing Label Assignment for Speech Separati...2020-10-29Code