U-Mamba-Net, a U-Net/Mamba hybrid, reaches 8.50 dB SI-SNRi on noisy-reverberant Libri2mix with 4.4M parameters and 2.5 GMACs, beating DPRNN by 0.42-0.91 dB at lower cost.
Mul- titalker speech separation with utterance-level permu- tation invariant training of deep recurrent neural net- works,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SD 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
U-Mamba-Net: A highly efficient Mamba-based U-net style network for noisy and reverberant speech separation
U-Mamba-Net, a U-Net/Mamba hybrid, reaches 8.50 dB SI-SNRi on noisy-reverberant Libri2mix with 4.4M parameters and 2.5 GMACs, beating DPRNN by 0.42-0.91 dB at lower cost.