Continual self-training with bootstrapped remixing for speech enhancement
Open paper
Benchmark
Model
Rank
Results
speech-enhancement-on-deep-noise-suppression
Sudo rm-rf (U=8)
#16
PESQ-WB: 2.69
SI-SDR-WB: 18.6
speech-enhancement-on-deep-noise-suppression
RemixIT (w Sudo U=32)
#18
PESQ-WB: 2.60
SI-SDR-WB: 18.0
Rank counts only results with a code link.