HyperAIHyperAI
HomeConsoleDocsNewsPapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Command Palette

Search for a command to run...

Speech Separation On Wsj0 2Mix

Metrics

Number of parameters (M)
SDRi
SI-SDRi

Results

Performance results of various models on this benchmark

Paper TitleRepository
SepReformer-L59.425.225.1Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation
TF-Locoformer (L) + DM22.525.225.1TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement
TF-Locoformer (M) + DM15.024.724.6TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement
TF-Locoformer (L)22.524.324.2TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement
MossFormer2 (L)55.7-24.1MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation
SepTDA (L=12)--24.0Boosting Unknown-number Speaker Separation with Transformer Decoder-based Attractor-
Separate And Diffuse--23.9Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separation-
TF-Locoformer (M)15.023.823.6TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement
TF-Locoformer (S) + DM5.02322.8TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement
MossFormer (L) + DM42.1-22.8MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions
SPGM + DM26.2-22.7SPGM: Prioritizing Local Features for enhanced speech separation performance
MossFormer (M) + DM--22.5MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions
SepIt--22.4SepIt: Approaching a Single Channel Speech Separation Bound-
SepFormer-22.422.3Attention is All You Need in Speech Separation
Wavesplit v2-22.322.2Wavesplit: End-to-End Speech Separation by Speaker Clustering-
SPGM26.2-22.1SPGM: Prioritizing Local Features for enhanced speech separation performance
TF-Locoformer (S)5.022.122TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement
DPTNet (Libri1Mix speech enhancement pre-trained)-21.521.3Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-training
TD-Conformer (XL) + DM--21.2On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments
Sandglasset--21.0Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separation
0 of 38 row(s) selected.
Speech Separation On Wsj0 2Mix | SOTA | HyperAI