mlsanityData to 7 Oct 2026

Supervised Speech Separation Based on Deep Learning: An Overview

arXiv 1708.07524 ↗First posted 24 Aug 2017cs.CL cs.LG cs.NEcited by 213

Not on the map. Why?

Cited by 37 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Speech separation is the task of separating target speech from background interference. Traditionally, speech separation is studied as a signal processing problem. A more recent approach formulates speech separation as a supervised learning problem, where the discriminative patterns of speech, speakers, and background noise are learned from training data. Over the past decade, many supervised separation algorithms have been put forward. In particular, the recent introduction of deep learning to supervised speech separation has dramatically accelerated progress and boosted separation performance. This article provides a comprehensive overview of the research on deep learning based supervised speech separation in the last several years. We first introduce the background of speech separation and the formulation of supervised separation. Then we discuss three main components of supervised separation: learning machines, training targets, and acoustic features. Much of the overview is on separation algorithms where we review monaural methods, including speech enhancement (speech-nonspeech separation), speaker separation (multi-talker separation), and speech dereverberation, as well as multi-microphone techniques. The important issue of generalization, unique to supervised learning, is discussed. This overview provides a historical perspective on how advances are made. In addition, we discuss a number of conceptual issues, including what constitutes the target source.

Key facts. Cited by 213 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Aug 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 36; 2022: 34; 2023: 44; 2024: 41; 2025: 32; 2026: 26.

213 papers.

Sort:

By area:

  1. 2022Speech Enhancement and Dereverberation with Diffusion-based Generative Modelscited by 195
  2. 2021A Review of Speaker Diarization: Recent Advances with Deep Learningcited by 122
  3. 2021MetricGAN+: An Improved Version of MetricGAN for Speech Enhancementcited by 114
  4. 2022StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberationcited by 105
  5. 2022SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilitiescited by 76
  6. 2023A Comprehensive Survey on Applications of Transformers for Deep Learning Taskscited by 70
  7. 2022Audio Self-supervised Learning: A Surveycited by 65
  8. 2024EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberationcited by 62
  9. 2024An Investigation of Incorporating Mamba for Speech Enhancementcited by 61
  10. 2021A Study on Speech Enhancement Based on Diffusion Probabilistic Modelcited by 52
  11. 2021A Survey of Sound Source Localization with Deep Learning Methodscited by 45
  12. 2022Separate What You Describe: Language-Queried Audio Source Separationcited by 45
38 more
  1. 2022CMGAN: Conformer-based Metric GAN for Speech Enhancementcited by 45
  2. 2023Separate Anything You Describecited by 43
  3. 2024A Large-Scale Evaluation of Speech Foundation Modelscited by 38
  4. 2022Analysing Diffusion-based Generative Approaches versus Discriminative Approaches for Speech Restorationcited by 34
  5. 2024Diffusion Models for Audio Restorationcited by 32
  6. 2023Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based Speech Enhancementcited by 30
  7. 2021Visual Scene Graphs for Audio Source Separationcited by 29
  8. 2021Variational Autoencoder for Speech Enhancement with a Noise-Aware Encodercited by 28
  9. 2021Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoderscited by 28
  10. 2022FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancementcited by 28
  11. 2022CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videoscited by 23
  12. 2022CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancementcited by 22
  13. 2023Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representationscited by 22
  14. 2024Action2Sound: Ambient-Aware Generation of Action Sounds from Egocentric Videoscited by 21
  15. 2024FlowSep: Language-Queried Sound Separation with Rectified Flow Matchingcited by 21
  16. 2025LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancementcited by 19
  17. 2021MetricGAN-U: Unsupervised speech enhancement/ dereverberation based only on noisy/ reverberated speechcited by 18
  18. 2021Dual-branch Attention-In-Attention Transformer for single-channel speech enhancementcited by 18
  19. 2021A Survey on Deep Reinforcement Learning for Audio-Based Applicationscited by 17
  20. 2021Unsupervised Noise Adaptive Speech Enhancement by Discriminator-Constrained Optimal Transportcited by 16
  21. 2023Target Speech Extraction with Conditional Diffusion Modelcited by 15
  22. 2023Single and Few-step Diffusion for Generative Speech Enhancementcited by 15
  23. 2022Heterogeneous Target Speech Separationcited by 13
  24. 2023A Sidecar Separator Can Convert a Single-Talker Speech Recognition System to a Multi-Talker Onecited by 13
  25. 2021Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstructioncited by 12
  26. 2023Unsupervised speech enhancement with diffusion-based generative modelscited by 12
  27. 2024Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealingcited by 12
  28. 2023Metric-oriented Speech Enhancement using Diffusion Probabilistic Modelcited by 11
  29. 2024Unsupervised Blind Joint Dereverberation and Room Acoustics Estimation with Diffusion Modelscited by 11
  30. 2025CoVoMix2: Advancing Zero-Shot Dialogue Generation with Fully Non-Autoregressive Flow Matchingcited by 11
  31. 2022L3DAS22 Challenge: Learning 3D Audio Sources in a Real Office Environmentcited by 10
  32. 2023Investigating the Design Space of Diffusion Models for Speech Enhancementcited by 10
  33. 2021L3DAS21 Challenge: Machine Learning for 3D Audio Signal Processingcited by 9
  34. 2022McNet: Fuse Multiple Cues for Multichannel Speech Enhancementcited by 9
  35. 2023Unsupervised Noise adaptation using Data Simulationcited by 9
  36. 2023Diffusion Posterior Sampling for Informed Single-Channel Dereverberationcited by 9
  37. 2024Cross-Speaker Encoding Network for Multi-Talker Speech Recognitioncited by 9
  38. 2024BUDDy: Single-Channel Blind Unsupervised Dereverberation with Diffusion Modelscited by 9

50 most cited of 213 All 213 (JSON)