TF-MossFormer: Integrating Convolution Gated Local-Global Attentions for Enhanced Time-Frequency Domain Monaural Speech Separation
Open paper
Benchmark
Model
Rank
Results
speech-separation-on-wsj0-2mix
TF-MossFormer(S)
–
SI-SDRi: 22.6
SDRi: 22.8
Number of parameters (M): 6.0
Rank counts only results with a code link.