CDiffuSE

Reported on 6 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio6 results

Speech EnhancementonEARS-WHAM
DNSMOS· 2022-02-10
2.87
best: 3.88 (SGMSE+)
Conditional Diffusion Probabilistic Model for Speech Enhancement arXiv:2202.05256
Speech EnhancementonEARS-WHAM
ESTOI· 2022-02-10
0.53
best: 0.73 (Schrödinger Bridge (PESQ loss))
Conditional Diffusion Probabilistic Model for Speech Enhancement arXiv:2202.05256
Speech EnhancementonEARS-WHAM
PESQ-WB· 2022-02-10
1.6
best: 3.09 (Schrödinger Bridge (PESQ loss))
Conditional Diffusion Probabilistic Model for Speech Enhancement arXiv:2202.05256
Speech EnhancementonEARS-WHAM
POLQA· 2022-02-10
1.81
best: 3.71 (Schrödinger Bridge (PESQ loss))
Conditional Diffusion Probabilistic Model for Speech Enhancement arXiv:2202.05256
Speech EnhancementonEARS-WHAM
SI-SDR· 2022-02-10
8.35
best: 17.85 (Schrödinger Bridge)
Conditional Diffusion Probabilistic Model for Speech Enhancement arXiv:2202.05256
Speech EnhancementonEARS-WHAM
SIGMOS· 2022-02-10
2.08
best: 3.44 (Schrödinger Bridge)
Conditional Diffusion Probabilistic Model for Speech Enhancement arXiv:2202.05256