Speech Enhancement and Dereverberation with Diffusion-based Generative Models
Open paper
Benchmark
Model
Rank
Results
speech-enhancement-on-ears-wham
SGMSE+
#2
PESQ-WB: 2.50
SI-SDR: 16.78
ESTOI: 0.73
SIGMOS: 3.41
DNSMOS: 3.88
…
speech-enhancement-on-demand
SGMSE+ (Diffusion Model)
#30
PESQ (wb): 2.93
Rank counts only results with a code link.