mlsanityData to 7 Oct 2026

Libri-Light: A Benchmark for ASR with Limited or No Supervision

arXiv 1912.07875 ↗First posted 17 Dec 2019cs.CL cs.SD eess.AScited by 462

Not on the map. Why?

Abstract (arXiv)

We introduce a new collection of spoken English audio suitable for training speech recognition systems under limited or no supervision. It is derived from open-source audio books from the LibriVox project. It contains over 60K hours of audio, which is, to our knowledge, the largest freely-available corpus of speech. The audio has been segmented using voice activity detection and is tagged with SNR, speaker ID and genre descriptions. Additionally, we provide baseline systems and evaluation metrics working under three settings: (1) the zero resource/unsupervised setting (ABX), (2) the semi-supervised setting (PER, CER) and (3) the distant supervision setting (WER). Settings (2) and (3) use limited textual resources (10 minutes to 10 hours) aligned with the speech. Setting (3) uses large amounts of unaligned text. They are evaluated on the standard LibriSpeech dev and test sets for comparison with the supervised state-of-the-art.

Key facts. Cited by 462 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 62; 2022: 87; 2023: 98; 2024: 111; 2025: 76; 2026: 28.

462 papers.

Sort:

By area:

  1. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  2. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,609
  3. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 737
  4. 2022data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Languagecited by 718
  5. 2022AudioLM: a Language Modeling Approach to Audio Generationcited by 611
  6. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 589
  7. 2023SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilitiescited by 518
  8. 2021VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretationcited by 455
  9. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 404
  10. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 373
  11. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 353
  12. 2021W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Trainingcited by 340
38 more
  1. 2021Generative Spoken Language Modeling from Raw Audiocited by 336
  2. 2021Layer-wise Analysis of a Self-supervised Speech Representation Modelcited by 293
  3. 2022Self-Supervised Speech Representation Learning: A Reviewcited by 258
  4. 2021Speech Resynthesis from Discrete Disentangled Self-Supervised Representationscited by 243
  5. 2023NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizerscited by 233
  6. 2024NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Modelscited by 222
  7. 2024Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generationcited by 200
  8. 2021Self-supervised Pretraining of Visual Features in the Wildcited by 197
  9. 2024XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Modelcited by 174
  10. 2023Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modelingcited by 166
  11. 2024MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformercited by 159
  12. 2022Self-supervised Learning with Random-projection Quantizer for Speech Recognitioncited by 158
  13. 2024Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Modelscited by 151
  14. 2021Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Trainingcited by 148
  15. 2021Direct speech-to-speech translation with discrete unitscited by 148
  16. 2021Unsupervised Speech Recognitioncited by 147
  17. 2021Self-Supervised Representation Learning: Introduction, Advances and Challengescited by 147
  18. 2023End-to-End Speech Recognition: A Surveycited by 127
  19. 2022Generative Spoken Dialogue Language Modelingcited by 125
  20. 2024WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modelingcited by 124
  21. 2023Audiobox: Unified Audio Generation with Natural Language Promptscited by 120
  22. 2021Text-Free Prosody-Aware Generative Spoken Language Modelingcited by 119
  23. 2024VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizerscited by 119
  24. 2024Large Language Models for Time Series: A Surveycited by 113
  25. 2023SoundStorm: Efficient Parallel Audio Generationcited by 111
  26. 2022Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Languagecited by 108
  27. 2023Textually Pretrained Speech Language Modelscited by 99
  28. 2021The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usagecited by 98
  29. 2023EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesiscited by 93
  30. 2023Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLMcited by 92
  31. 2022E-Branchformer: Branchformer with Enhanced merging for speech recognitioncited by 90
  32. 2021BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognitioncited by 88
  33. 2023VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translationcited by 87
  34. 2024An Embarrassingly Simple Approach for LLM with Strong ASR Capacitycited by 86
  35. 2024Recent Advances in Speech Language Models: A Surveycited by 85
  36. 2021SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Networkcited by 83
  37. 2021A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understandingcited by 82
  38. 2021Simple and Effective Zero-shot Cross-lingual Phoneme Recognitioncited by 79

50 most cited of 462 All 462 (JSON)