SepReformer-L + DM

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

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

Speech2 results

Speech SeparationonWHAMR!
SI-SDRi· 2024-06-10
17.1
best: 18.5 (TF-Locoformer (M))
SOTA
Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation arXiv:2406.05983
Speech SeparationonWHAM!
SI-SDRi· 2024-06-10
18.4
SOTA
Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation arXiv:2406.05983