Datasets › WSJ0-2mix

WSJ0-2mix

Introduced by John R. Hershey et al. in Deep clustering: Discriminative embeddings for segmentation and separation18 Aug 2015 archive 2025-07-28

WSJ0-2mix is a speech recognition corpus of speech mixtures using utterances from the Wall Street Journal (WSJ0) corpus.

Source: Deep clustering: Discriminative embeddings for segmentation and separation

Benchmarks archive 2025-07-28

All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Speech Separation WSJ0-2mix TF-Locoformer (L) + DM SI-SDRi 25.1 TF-Locoformer: Transformer with Local Modeling by... merlresearch/tf-locoformer 40 Compare
Adversarial Attack WSJ0-2mix ConvTasnet and Dual Path Transformers SDR 0.70dB Harmonicity Plays a Critical Role in DNN Based Versus in... — 1 Compare
Speech Separation WSJ0-2mix-16k MossFormer2 SI-SDRi 20.5 MossFormer: Pushing the Performance Limit of Monaural... modelscope/ClearerVoice-Studio +1 1 Compare

Papers archive 2025-07-28

papers with a benchmark row: 31 · with a code link: 26 · where Syntology ran a sample: 10 (7 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (10 of 31 with a benchmark row: 7 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 31 of 31 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 159. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
SepMamba: State-space models for speaker separation using Mamba 1 2 28 Oct 2024 not harvested
TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement 1 6 6 Aug 2024 not harvested
Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation 1 1 10 Jun 2024 not harvested
Boosting Unknown-number Speaker Separation with Transformer Decoder-based Attractor 0 1 23 Jan 2024 not harvested
On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments 1 1 9 Oct 2023 not harvested
SPGM: Prioritizing Local Features for enhanced speech separation performance 1 2 22 Sep 2023 not harvested
MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions 2 3 23 Feb 2023 official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (1 pointer-only for licence)
Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separation 0 1 25 Jan 2023 not harvested
Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation 2 2 27 Oct 2022 not harvested
SepIt: Approaching a Single Channel Speech Separation Bound 0 1 24 May 2022 not harvested
Harmonicity Plays a Critical Role in DNN Based Versus in Biologically-Inspired Monaural Speech Segregation Systems 0 1 8 Mar 2022 not harvested
Compute and memory efficient universal sound source separation 3 1 3 Mar 2021 not harvested
Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separation 2 1 1 Mar 2021 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (1 pointer-only for licence)
Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networks 2 1 13 Jan 2021 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (1 pointer-only for licence)
Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-training 1 1 29 Oct 2020 not harvested
Attention is All You Need in Speech Separation 4 1 25 Oct 2020 not harvested
Sudo rm -rf: Efficient Networks for Universal Audio Source Separation 4 1 14 Jul 2020 official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (1 pointer-only for licence)
Voice Separation with an Unknown Number of Multiple Speakers 4 1 29 Feb 2020 official (archive's flag): 1 ran · 12 ran (of which 5 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (9 pointer-only for licence)
Wavesplit: End-to-End Speech Separation by Speaker Clustering 0 2 20 Feb 2020 not harvested
Interrupted and cascaded permutation invariant training for speech separation 1 1 28 Oct 2019 not harvested
Two-Step Sound Source Separation: Training on Learned Latent Targets 2 1 22 Oct 2019 not harvested
Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation 8 1 14 Oct 2019 19 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 1 honoured, 1 violated, 15 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified
Divide and Conquer: A Deep CASA Approach to Talker-independent Monaural Speaker Separation 1 1 25 Apr 2019 not harvested
Improved Speech Separation with Time-and-Frequency Cross-domain Joint Embedding and Clustering 1 1 16 Apr 2019 not harvested
Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation 17 1 20 Sep 2018 community repositories only · 28 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 3 honoured, 2 violated, 17 with no contract checked; 6 where Syntology's instrument failed) · 8 unverified (16 pointer-only for licence)
Real-time Single-channel Dereverberation and Separation with Time-domainAudio Separation Network 1 1 2 Sep 2018 not harvested
Alternative Objective Functions for Deep Clustering 1 1 1 Apr 2018 not harvested
TasNet: time-domain audio separation network for real-time, single-channel speech separation 3 1 1 Nov 2017 not harvested
Deep clustering: Discriminative embeddings for segmentation and separation 8 1 18 Aug 2015 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (3 pointer-only for licence)
Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation 6 1 official: no sample here; runs from other or unrecorded repositories · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (2 pointer-only for licence)
MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation 2 1 official (archive's flag): 1 ran · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (2 pointer-only for licence)

Dataset loaders archive 2025-07-28

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • WSJ0-2mix
  • WSJ0-2mix-16k

2 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections