SepReformer-L

Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA

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

Speech4 results

Speech SeparationonWSJ0-2mix
MACs (G)· 2024-06-10
155.5
SOTA
Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation arXiv:2406.05983
Speech SeparationonWSJ0-2mix
Number of parameters (M)· 2024-06-10
59.4
SOTA
Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation arXiv:2406.05983
Speech SeparationonWSJ0-2mix
SDRi· 2024-06-10
25.2
SOTA
Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation arXiv:2406.05983
Speech SeparationonWSJ0-2mix
SI-SDRi· 2024-06-10
25.1
SOTA
Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation arXiv:2406.05983