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/Audio/Speech Enhancement/EARS-WHAM

Speech Enhancement on EARS-WHAM

Metric: ESTOI (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕ESTOI▼Extra DataPaperDate↕Code
1Schrödinger Bridge (PESQ loss)0.73NoInvestigating Training Objectives for Generative...2024-09-16Code
2SGMSE+0.73NoSpeech Enhancement and Dereverberation with Diff...2022-08-11Code
3Schrödinger Bridge0.73NoSchrödinger Bridge for Generative Speech Enhance...2024-07-22-
4Demucs v40.71NoHybrid Transformers for Music Source Separation2022-11-15Code
5Conv-TasNet0.7NoConv-TasNet: Surpassing Ideal Time-Frequency Mag...2018-09-20Code
6CDiffuSE0.53NoConditional Diffusion Probabilistic Model for Sp...2022-02-10Code