Speech Separation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

19 leaderboard tables shown for this task, 19 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 19 until expanded.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

16 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 120 papers with code (359 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
  20 Sep 2018 17 repositories listed Syntology ran 7 of 36 samples · 29 unverified · 16 pointer-only (licence)
  The majority of the previous methods have formulated the separation problem through the time-frequency representation of the mixed signal, which has several drawbacks, including the decoupling of the phase and magnitude…
• Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation
  14 Oct 2019 8 repositories listed Syntology ran 4 of 22 samples · 18 unverified
  Recent studies in deep learning-based speech separation have proven the superiority of time-domain approaches to conventional time-frequency-based methods.
• Deep clustering: Discriminative embeddings for segmentation and separation
  18 Aug 2015 8 repositories listed Syntology ran 2 of 3 samples · 1 unverified · 3 pointer-only (licence)
  The framework can be used without class labels, and therefore has the potential to be trained on a diverse set of sound types, and to generalize to novel sources.
• WaveCRN: An Efficient Convolutional Recurrent Neural Network for End-to-end Speech Enhancement
  6 Apr 2020 5 repositories listed
  In WaveCRN, the speech locality feature is captured by a convolutional neural network (CNN), while the temporal sequential property of the locality feature is modeled by stacked simple recurrent units (SRU).
• Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis
  13 Jul 2024 4 repositories listed
  It is too early to conclude that Mamba is a better alternative to transformers for speech before comparing Mamba with transformers in terms of both performance and efficiency in multiple speech-related tasks.
• Attention is All You Need in Speech Separation
  25 Oct 2020 4 repositories listed
  Transformers are emerging as a natural alternative to standard RNNs, replacing recurrent computations with a multi-head attention mechanism.
• Sudo rm -rf: Efficient Networks for Universal Audio Source Separation
  14 Jul 2020 4 repositories listed Syntology ran 1 of 10 samples · 9 unverified
  In this paper, we present an efficient neural network for end-to-end general purpose audio source separation.
• Voice Separation with an Unknown Number of Multiple Speakers
  29 Feb 2020 4 repositories listed Syntology ran 10 of 13 samples · 3 unverified · 9 pointer-only (licence)
  We present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously.
• Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation
  10 Apr 2018 4 repositories listed Syntology ran 0 of 23 samples · 23 unverified
  Solving this task using only audio as input is extremely challenging and does not provide an association of the separated speech signals with speakers in the video.
• Compute and memory efficient universal sound source separation
  3 Mar 2021 3 repositories listed
  Recent progress in audio source separation lead by deep learning has enabled many neural network models to provide robust solutions to this fundamental estimation problem.
• TasNet: time-domain audio separation network for real-time, single-channel speech separation
  1 Nov 2017 3 repositories listed
  We directly model the signal in the time-domain using an encoder-decoder framework and perform the source separation on nonnegative encoder outputs.
• Multi-talker Speech Separation with Utterance-level Permutation Invariant Training of Deep Recurrent Neural Networks
  18 Mar 2017 3 repositories listed Syntology ran 1 of 3 samples · 2 unverified · 3 pointer-only (licence)
  We evaluated uPIT on the WSJ0 and Danish two- and three-talker mixed-speech separation tasks and found that uPIT outperforms techniques based on Non-negative Matrix Factorization (NMF) and Computational Auditory Scene…
• SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios
  2 Oct 2024 2 repositories listed Syntology ran 8 of 11 samples · 3 unverified · 11 pointer-only (licence)
  Additionally, to investigate the differences between synthetic and real-world data, we selected 5 hours of raw, non-reverberant data from the SonicSet validation set and recorded a real-world speech separation dataset,…
• MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions
  23 Feb 2023 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  To effectively solve the indirect elemental interactions across chunks in the dual-path architecture, MossFormer employs a joint local and global self-attention architecture that simultaneously performs a…
• An Audio-Visual Speech Separation Model Inspired by Cortico-Thalamo-Cortical Circuits
  21 Dec 2022 2 repositories listed Syntology ran 2 of 3 samples · 1 unverified
  Then, inspired by the large number of connections between cortical regions and the thalamus, the model fuses the auditory and visual information in a thalamic subnetwork through top-down connections.
• Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation
  27 Oct 2022 2 repositories listed
  In this work deformable convolution is proposed as a solution to allow TCN models to have dynamic RFs that can adapt to various reverberation times for reverberant speech separation.
• CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement
  22 Sep 2022 2 repositories listed
  Rather than focusing exclusively on the speech denoising task, we extend this work to address the dereverberation and super-resolution tasks.
• MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenes
  18 May 2022 2 repositories listed Syntology ran 6 of 6 samples · 0 unverified · 6 pointer-only (licence)
  We show that the acoustic metrics of the IRs predicted from our MESH2IR match the ground truth with less than 10% error.
• A cappella: Audio-visual Singing Voice Separation
  20 Apr 2021 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  The task of isolating a target singing voice in music videos has useful applications.
• Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separation
  1 Mar 2021 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  One of the leading single-channel speech separation (SS) models is based on a TasNet with a dual-path segmentation technique, where the size of each segment remains unchanged throughout all layers.
• Directional Sparse Filtering using Weighted Lehmer Mean for Blind Separation of Unbalanced Speech Mixtures
  30 Jan 2021 2 repositories listed
  In blind source separation of speech signals, the inherent imbalance in the source spectrum poses a challenge for methods that rely on single-source dominance for the estimation of the mixing matrix.
• Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networks
  13 Jan 2021 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  Recent research on the time-domain audio separation networks (TasNets) has brought great success to speech separation.
• Multi-Decoder DPRNN: High Accuracy Source Counting and Separation
  24 Nov 2020 2 repositories listed
  Beyond the model, we also propose a metric on how to evaluate source separation with variable number of speakers.
• Multi-microphone Complex Spectral Mapping for Utterance-wise and Continuous Speech Separation
  4 Oct 2020 2 repositories listed Syntology ran 1 of 9 samples · 8 unverified
  Although our system is trained on simulated room impulse responses (RIR) based on a fixed number of microphones arranged in a given geometry, it generalizes well to a real array with the same geometry.
• End-to-end Microphone Permutation and Number Invariant Multi-channel Speech Separation
  30 Oct 2019 2 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  An important problem in ad-hoc microphone speech separation is how to guarantee the robustness of a system with respect to the locations and numbers of microphones.
• Filterbank design for end-to-end speech separation
  23 Oct 2019 2 repositories listed Syntology ran 1 of 8 samples · 7 unverified
  Also, we validate the use of parameterized filterbanks and show that complex-valued representations and masks are beneficial in all conditions.
• Two-Step Sound Source Separation: Training on Learned Latent Targets
  22 Oct 2019 2 repositories listed
  In the first step we learn a transform (and it's inverse) to a latent space where masking-based separation performance using oracles is optimal.
• Single-Channel Multi-Speaker Separation using Deep Clustering
  7 Jul 2016 2 repositories listed
  In this paper we extend the baseline system with an end-to-end signal approximation objective that greatly improves performance on a challenging speech separation.
• Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation
  13 Feb 2015 2 repositories listed
  In this paper, we explore joint optimization of masking functions and deep recurrent neural networks for monaural source separation tasks, including monaural speech separation, monaural singing voice separation, and…
• SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline
  25 May 2025 1 repository listed
  On the other hand, generative models for TSE lag in perceptual quality and intelligibility.

Syntology lines on 17 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.