mlsanityData to 7 Oct 2026

LibriMix: An Open-Source Dataset for Generalizable Speech Separation

arXiv 2005.11262 ↗First posted 22 May 2020eess.AScited by 154

Not on the map. Why?

Abstract (arXiv)

In recent years, wsj0-2mix has become the reference dataset for single-channel speech separation. Most deep learning-based speech separation models today are benchmarked on it. However, recent studies have shown important performance drops when models trained on wsj0-2mix are evaluated on other, similar datasets. To address this generalization issue, we created LibriMix, an open-source alternative to wsj0-2mix, and to its noisy extension, WHAM!. Based on LibriSpeech, LibriMix consists of two- or three-speaker mixtures combined with ambient noise samples from WHAM!. Using Conv-TasNet, we achieve competitive performance on all LibriMix versions. In order to fairly evaluate across datasets, we introduce a third test set based on VCTK for speech and WHAM! for noise. Our experiments show that the generalization error is smaller for models trained with LibriMix than with WHAM!, in both clean and noisy conditions. Aiming towards evaluation in more realistic, conversation-like scenarios, we also release a sparsely overlapping version of LibriMix's test set.

Key facts. Cited by 154 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 17; 2023: 23; 2024: 32; 2025: 35; 2026: 32.

154 papers.

Sort:

By area:

  1. 2021SUPERB: Speech processing Universal PERformance Benchmarkcited by 652
  2. 2023SALMONN: Towards Generic Hearing Abilities for Large Language Modelscited by 492
  3. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 404
  4. 2022SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilitiescited by 76
  5. 2023Generative Pre-training for Speech with Flow Matchingcited by 55
  6. 2023Separate Anything You Describecited by 43
  7. 2022Diffusion-based Generative Speech Source Separationcited by 41
  8. 2022An efficient encoder-decoder architecture with top-down attention for speech separationcited by 38
  9. 2024A Large-Scale Evaluation of Speech Foundation Modelscited by 38
  10. 2025Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Surveycited by 38
  11. 2024DASB - Discrete Audio and Speech Benchmarkcited by 32
  12. 2025SepPrune: Structured Pruning for Efficient Deep Speech Separationcited by 31
38 more
  1. 2022MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenescited by 23
  2. 2024Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?cited by 23
  3. 2025AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancementcited by 23
  4. 2024Speech Robust Bench: A Robustness Benchmark For Speech Recognitioncited by 20
  5. 2025LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancementcited by 19
  6. 2025FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networkscited by 18
  7. 2022SepIt: Approaching a Single Channel Speech Separation Boundcited by 16
  8. 2023Target Speech Extraction with Conditional Diffusion Modelcited by 15
  9. 2023Extending Whisper with prompt tuning to target-speaker ASRcited by 14
  10. 2023A Sidecar Separator Can Convert a Single-Talker Speech Recognition System to a Multi-Talker Onecited by 13
  11. 2021Many-Speakers Single Channel Speech Separation with Optimal Permutation Trainingcited by 11
  12. 2024Empowering Whisper as a Joint Multi-Talker and Target-Talker Speech Recognition Systemcited by 11
  13. 2023Unifying Speech Enhancement and Separation with Gradient Modulation for End-to-End Noise-Robust Speech Separationcited by 10
  14. 2024Advancing Multi-talker ASR Performance with Large Language Modelscited by 10
  15. 2024TSELM: Target Speaker Extraction using Discrete Tokens and Language Modelscited by 10
  16. 2024TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separationcited by 10
  17. 2024Noise-robust Speech Separation with Fast Generative Correctioncited by 9
  18. 2025SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipelinecited by 9
  19. 2023MiniSUPERB: Lightweight Benchmark for Self-supervised Speech Modelscited by 8
  20. 2023TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognitioncited by 8
  21. 2023DDTSE: Discriminative Diffusion Model for Target Speech Extractioncited by 8
  22. 2025FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillationcited by 8
  23. 2021Configurable Privacy-Preserving Automatic Speech Recognitioncited by 7
  24. 2021REAL-M: Towards Speech Separation on Real Mixturescited by 7
  25. 2022MixCycle: Unsupervised Speech Separation via Cyclic Mixture Permutation Invariant Trainingcited by 7
  26. 2022Improving the Naturalness of Simulated Conversations for End-to-End Neural Diarizationcited by 7
  27. 2023Unified Modeling of Multi-Talker Overlapped Speech Recognition and Diarization with a Sidecar Separatorcited by 7
  28. 2024Serialized Speech Information Guidance with Overlapped Encoding Separation for Multi-Speaker Automatic Speech Recognitioncited by 7
  29. 2023Cocktail HuBERT: Generalized Self-Supervised Pre-training for Mixture and Single-Source Speechcited by 6
  30. 2023A Neural State-Space Model Approach to Efficient Speech Separationcited by 6
  31. 2023GASS: Generalizing Audio Source Separation with Large-scale Datacited by 6
  32. 2025FlowTSE: Target Speaker Extraction with Flow Matchingcited by 6
  33. 2021Characterizing the adversarial vulnerability of speech self-supervised learningcited by 5
  34. 2021Directed Speech Separation for Automatic Speech Recognition of Long Form Conversational Speechcited by 5
  35. 2024Serialized Output Training by Learned Dominancecited by 5
  36. 2025LauraTSE: Target Speaker Extraction using Auto-Regressive Decoder-Only Language Modelscited by 5
  37. 2025Serialized Output Prompting for Large Language Model-based Multi-Talker Speech Recognitioncited by 5
  38. 2021On permutation invariant training for speech source separationcited by 4

50 most cited of 154 All 154 (JSON)