WSJ0-2mix

Overview edit

Variants: WSJ0-2mix, WSJ0-2mix-16k

Associated Benchmarks

This dataset is used in 2 benchmarks:

• Speech Separation - Metrics: SI-SDRi, SDRi, Number of parameters (M), MACs (G)
• Adversarial Attack - Metrics: SDR

Recent Benchmark Submissions

Research Papers

Recent papers with results on this dataset:

• SepMamba: State-space models for speaker separation using Mamba (2024) -
• TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement (2024) -
• Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation (2024) -
• Boosting Unknown-number Speaker Separation with Transformer Decoder-based Attractor (2024) -
• On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments (2023) -
• SPGM: Prioritizing Local Features for enhanced speech separation performance (2023) -
• MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions (2023) -
• Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separation (2023) -
• Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation (2022) -
• SepIt: Approaching a Single Channel Speech Separation Bound (2022) -
• Harmonicity Plays a Critical Role in DNN Based Versus in Biologically-Inspired Monaural Speech Segregation Systems (2022) -
• Compute and memory efficient universal sound source separation (2021) -
• Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separation (2021) -
• Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networks (2021) -
• Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-training (2020) -
• Attention is All You Need in Speech Separation (2020) -
• Sudo rm -rf: Efficient Networks for Universal Audio Source Separation (2020) -
• Voice Separation with an Unknown Number of Multiple Speakers (2020) -
• Wavesplit: End-to-End Speech Separation by Speaker Clustering (2020) -
• Interrupted and cascaded permutation invariant training for speech separation (2019) -