OpenCodePapers

speech-separation-on-whamr

Speech Separation
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeSI-SDRiMACs (G)Number of parameters (M)SDRiModelNameReleaseDate
TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement✓ Link18.51516.9TF-Locoformer (M)2024-08-06
TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement✓ Link17.4515.9TF-Locoformer (S)2024-08-06
Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation✓ Link17.1SepReformer-L + DM2024-06-10
MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation✓ Link17.0MossFormer22023-12-19
MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions✓ Link16.3MossFormer (L) + DM2023-02-23
On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments✓ Link14.6TD-Conformer (XL) + DM2023-10-09
Compute and memory efficient universal sound source separation✓ Link13.5Improved Sudo rm -rf (U=36)2021-03-03
On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments✓ Link13.4TD-Conformer (L) + DM2023-10-09
Wavesplit: End-to-End Speech Separation by Speaker Clustering13.2Wavesplit2020-02-20
Stepwise-Refining Speech Separation Network via Fine-Grained Encoding in High-order Latent Domain12.3DPTNET - SRSSN2021-10-10
Stepwise-Refining Speech Separation Network via Fine-Grained Encoding in High-order Latent Domain12.3DPRNN - SRSSN2021-10-10
Voice Separation with an Unknown Number of Multiple Speakers✓ Link12.2VSUNOS2020-02-29
Sudo rm -rf: Efficient Networks for Universal Audio Source Separation✓ Link12.1Sudo rm -rf (U=16)2020-07-14
On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments✓ Link12TD-Confomer (M) + DM2023-10-09
Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation✓ Link11.13.73.610.3Deformable TCN + Dynamic Mixing2022-10-27
On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments✓ Link10.5TD-Confomer (S)2023-10-09
Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation✓ Link10.13.71.39.5Deformable TCN + Shared Weights + Dynamic Mixing2022-10-27
WHAM!: Extending Speech Separation to Noisy Environments✓ Link9.2Bi-LSTM-TASNET2019-07-02
Check out how to contribute new results.