Speech Enhancement on EARS-WHAM

Metric: ESTOI (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	ESTOI▼	Extra Data	Paper	Date↕	Code
1	Schrödinger Bridge (PESQ loss)	0.73	No	Investigating Training Objectives for Generative...	2024-09-16	Code
2	SGMSE+	0.73	No	Speech Enhancement and Dereverberation with Diff...	2022-08-11	Code
3	Schrödinger Bridge	0.73	No	Schrödinger Bridge for Generative Speech Enhance...	2024-07-22	-
4	Demucs v4	0.71	No	Hybrid Transformers for Music Source Separation	2022-11-15	Code
5	Conv-TasNet	0.7	No	Conv-TasNet: Surpassing Ideal Time-Frequency Mag...	2018-09-20	Code
6	CDiffuSE	0.53	No	Conditional Diffusion Probabilistic Model for Sp...	2022-02-10	Code

#1Schrödinger Bridge (PESQ loss)
0.73
ESTOI· 2024-09-16
Investigating Training Objectives for Generative Speech Enhancement Code
#2SGMSE+SOTA
0.73
ESTOI· 2022-08-11
Speech Enhancement and Dereverberation with Diffusion-based Generative Models Code
#3Schrödinger Bridge
0.73
ESTOI· 2024-07-22
Schrödinger Bridge for Generative Speech Enhancement
#4Demucs v4
0.71
ESTOI· 2022-11-15
Hybrid Transformers for Music Source Separation Code
#5Conv-TasNetSOTA
0.7
ESTOI· 2018-09-20
Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation Code
#6CDiffuSE
0.53
ESTOI· 2022-02-10
Conditional Diffusion Probabilistic Model for Speech Enhancement Code