Speech Enhancement on Libri-TUT benchmark leaderboard · SOTA2 Research

Speech Enhancement on Libri-TUT

4.64PESQClean

Evaluation Results

Method	Links
Clean2026.02		4.64	1	—	0	3.73	3.31	3.06	3.98	1	1
Clean-NAC2026.02		2.93	0.89	3.51	2.88	3.75	3.33	3.01	3.9	0.97	0.96
BSRNN2026.02		2.77	0.88	16.77	5.23	3.79	3.59	3.16	3.94	0.96	0.89
Conv-TasNet2026.02		2.44	0.85	15.88	5.03	3.58	3.27	2.68	3.49	0.93	0.85
EDM-SE2026.02		2.38	0.83	13.69	4.34	3.75	3.37	3.02	3.67	0.92	0.87
NAC-SE2026.02		2.04	0.79	2.61	4.6	3.69	3.15	2.97	3.8	0.87	0.84
SGMSE+2026.02		1.96	0.77	11.57	5.08	3.36	2.66	2.52	3	0.91	0.83
ADDSE-XL2026.02		1.68	0.72	1.1	5.83	3.76	3.43	2.9	3.52	0.79	0.78
ADDSE-L2026.02		1.66	0.71	1.01	5.85	3.75	3.41	2.89	3.46	0.78	0.77
ADDSE-M2026.02		1.62	0.7	0.89	5.95	3.74	3.41	2.88	3.38	0.76	0.76
ADDSE-S2026.02		1.56	0.69	0.76	6.04	3.72	3.4	2.78	3.18	0.71	0.73
EDM-NAC-SE2026.02		1.54	0.69	0.56	6.06	3.7	3.38	2.69	3.1	0.73	0.74
ADDSE-XS2026.02		1.48	0.66	0.55	6.31	3.67	3.38	2.66	2.86	0.65	0.7
Noisy2026.02		1.31	0.61	4.96	6.76	2.92	2.03	2.44	2.47	0.82	0.73