Speech Enhancement on EARS-WHAM

Metric: PESQ-WB (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	PESQ-WB▼	Extra Data	Paper	Date↕	Code
1	Schrödinger Bridge (PESQ loss)	3.09	No	Investigating Training Objectives for Generative...	2024-09-16	Code
2	SGMSE+	2.5	No	Speech Enhancement and Dereverberation with Diff...	2022-08-11	Code
3	Demucs v4	2.37	No	Hybrid Transformers for Music Source Separation	2022-11-15	Code
4	Schrödinger Bridge	2.33	No	Schrödinger Bridge for Generative Speech Enhance...	2024-07-22	-
5	Conv-TasNet	2.31	No	Conv-TasNet: Surpassing Ideal Time-Frequency Mag...	2018-09-20	Code
6	CDiffuSE	1.6	No	Conditional Diffusion Probabilistic Model for Sp...	2022-02-10	Code

#1Schrödinger Bridge (PESQ loss)SOTA
3.09
PESQ-WB· 2024-09-16
Investigating Training Objectives for Generative Speech Enhancement Code
#2SGMSE+SOTA
2.5
PESQ-WB· 2022-08-11
Speech Enhancement and Dereverberation with Diffusion-based Generative Models Code
#3Demucs v4
2.37
PESQ-WB· 2022-11-15
Hybrid Transformers for Music Source Separation Code
#4Schrödinger Bridge
2.33
PESQ-WB· 2024-07-22
Schrödinger Bridge for Generative Speech Enhancement
#5Conv-TasNetSOTA
2.31
PESQ-WB· 2018-09-20
Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation Code
#6CDiffuSE
1.6
PESQ-WB· 2022-02-10
Conditional Diffusion Probabilistic Model for Speech Enhancement Code