|
TF-Locoformer (L) + DM
|
TF-Locoformer: Transformer with Local Modeling by…
|
25.10
|
2024-08-06
|
|
|
SepReformer-L
|
Separate and Reconstruct: Asymmetric Encoder-Deco…
|
25.10
|
2024-06-10
|
|
|
TF-Locoformer (M) + DM
|
TF-Locoformer: Transformer with Local Modeling by…
|
24.60
|
2024-08-06
|
|
|
TF-Locoformer (L)
|
TF-Locoformer: Transformer with Local Modeling by…
|
24.20
|
2024-08-06
|
|
|
SepTDA (L=12)
|
Boosting Unknown-number Speaker Separation with T…
|
24.00
|
2024-01-23
|
|
|
Separate And Diffuse
|
Separate And Diffuse: Using a Pretrained Diffusio…
|
23.90
|
2023-01-25
|
|
|
TF-Locoformer (M)
|
TF-Locoformer: Transformer with Local Modeling by…
|
23.60
|
2024-08-06
|
|
|
TF-Locoformer (S) + DM
|
TF-Locoformer: Transformer with Local Modeling by…
|
22.80
|
2024-08-06
|
|
|
MossFormer (L) + DM
|
MossFormer: Pushing the Performance Limit of Mona…
|
22.80
|
2023-02-23
|
|
|
SepMamba + DM (M)
|
SepMamba: State-space models for speaker separati…
|
22.70
|
2024-10-28
|
|
|
SPGM + DM
|
SPGM: Prioritizing Local Features for enhanced sp…
|
22.70
|
2023-09-22
|
|
|
MossFormer (M) + DM
|
MossFormer: Pushing the Performance Limit of Mona…
|
22.50
|
2023-02-23
|
|
|
SepIt
|
SepIt: Approaching a Single Channel Speech Separa…
|
22.40
|
2022-05-24
|
|
|
SepFormer
|
Attention is All You Need in Speech Separation
|
22.30
|
2020-10-25
|
|
|
Wavesplit v2
|
Wavesplit: End-to-End Speech Separation by Speake…
|
22.20
|
2020-02-20
|
|
|
SPGM
|
SPGM: Prioritizing Local Features for enhanced sp…
|
22.10
|
2023-09-22
|
|
|
TF-Locoformer (S)
|
TF-Locoformer: Transformer with Local Modeling by…
|
22.00
|
2024-08-06
|
|
|
DPTNet (Libri1Mix speech enhancement pre-trained)
|
Stabilizing Label Assignment for Speech Separatio…
|
21.30
|
2020-10-29
|
|
|
SepMamba + DM (S)
|
SepMamba: State-space models for speaker separati…
|
21.20
|
2024-10-28
|
|
|
TD-Conformer (XL) + DM
|
On Time Domain Conformer Models for Monaural Spee…
|
21.20
|
2023-10-09
|
|
|
Sandglasset
|
Sandglasset: A Light Multi-Granularity Self-atten…
|
21.00
|
2021-03-01
|
|
|
GALR
|
Effective Low-Cost Time-Domain Audio Separation U…
|
20.30
|
2021-01-13
|
|
|
Gated DualPathRNN
|
Voice Separation with an Unknown Number of Multip…
|
20.12
|
2020-02-29
|
|
|
Sudo rm -rf (U=36)
|
Compute and memory efficient universal sound sour…
|
19.50
|
2021-03-03
|
|
|
Wavesplit v1
|
Wavesplit: End-to-End Speech Separation by Speake…
|
19.00
|
2020-02-20
|
|
|
Sudo rm -rf XL
|
Sudo rm -rf: Efficient Networks for Universal Aud…
|
18.90
|
2020-07-14
|
|
|
Dual-path RNN
|
Dual-path RNN: efficient long sequence modeling f…
|
18.80
|
2019-10-14
|
|
|
DeepCASA
|
Divide and Conquer: A Deep CASA Approach to Talke…
|
17.70
|
2019-04-25
|
|
|
IAC-PIT Tasnet
|
Interrupted and cascaded permutation invariant tr…
|
17.50
|
2019-10-28
|
|
|
Deformable TCN + Dynamic Mixing
|
Deformable Temporal Convolutional Networks for Mo…
|
17.20
|
2022-10-27
|
|
|
Hybrid-Tasnet
|
Improved Speech Separation with Time-and-Frequenc…
|
16.60
|
2019-04-16
|
|
|
Deformable TCN + Shared Weights + Dynamic Mixing
|
Deformable Temporal Convolutional Networks for Mo…
|
16.10
|
2022-10-27
|
|
|
Two-step Conv-TasNet
|
Two-Step Sound Source Separation: Training on Lea…
|
16.10
|
2019-10-22
|
|
|
Conv-TasNet
|
Conv-TasNet: Surpassing Ideal Time-Frequency Magn…
|
15.30
|
2018-09-20
|
|
|
TasNet
|
TasNet: time-domain audio separation network for …
|
10.80
|
2017-11-01
|
|
|
Deep Clustering ++
|
Deep clustering: Discriminative embeddings for se…
|
10.80
|
2015-08-18
|
|