mlsanityData to 7 Oct 2026

Robust Speech Recognition via Large-Scale Weak Supervision

arXiv 2212.04356 ↗First posted 6 Dec 2022eess.AS cs.CL cs.LGcited by 3,972

Not on the map. Why?

Cited by 161 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual and multitask supervision, the resulting models generalize well to standard benchmarks and are often competitive with prior fully supervised results but in a zero-shot transfer setting without the need for any fine-tuning. When compared to humans, the models approach their accuracy and robustness. We are releasing models and inference code to serve as a foundation for further work on robust speech processing.

Key facts. Cited by 3,972 papers in the map (data through 7 Oct 2026). Builds on 57 of its 100 references that are in the map. First posted on arXiv 6 Dec 2022.

Builds on

57 of 100 references.

References · 57

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  7. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  8. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  9. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  10. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  11. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  12. 2019Generating Long Sequences with Sparse Transformerscited by 1,523
38 more
  1. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  2. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  3. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  4. 2016Deep Networks with Stochastic Depthcited by 973
  5. 2016Training Deep Nets with Sublinear Memory Costcited by 825
  6. 2019Big Transfer (BiT): General Visual Representation Learningcited by 766
  7. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 604
  8. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 589
  9. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 568
  10. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 467
  11. 2020MLS: A Large-Scale Multilingual Dataset for Speech Researchcited by 467
  12. 2022FLEURS: Few-shot Learning Evaluation of Universal Representations of Speechcited by 458
  13. 2021VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretationcited by 455
  14. 2020Measuring Robustness to Natural Distribution Shifts in Image Classificationcited by 452
  15. 2015Deep Speech 2: End-to-End Speech Recognition in English and Mandarincited by 449
  16. 2021GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audiocited by 391
  17. 2020Pretrained Transformers Improve Out-of-Distribution Robustnesscited by 293
  18. 2016Using the Output Embedding to Improve Language Modelscited by 266
  19. 2018The Natural Language Decathlon: Multitask Learning as Question Answeringcited by 235
  20. 2019NeMo: a toolkit for building AI applications using Neural Modulescited by 230
  21. 2018TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptationcited by 224
  22. 2019BPE-Dropout: Simple and Effective Subword Regularizationcited by 189
  23. 2020Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognitioncited by 185
  24. 2020fairseq S2T: Fast Speech-to-Text Modeling with fairseqcited by 174
  25. 2021Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Trainingcited by 148
  26. 2021Unsupervised Speech Recognitioncited by 147
  27. 2018Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objectscited by 143
  28. 2020CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordingscited by 129
  29. 2020VoxLingua107: a Dataset for Spoken Language Recognitioncited by 118
  30. 2020Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameterscited by 110
  31. 2021Scaling Laws for Neural Machine Translationcited by 110
  32. 2022mSLAM: Massively multilingual joint pre-training for speech and textcited by 108
  33. 2020The Effect of Natural Distribution Shift on Question Answering Modelscited by 104
  34. 2020Self-training and Pre-training are Complementary for Speech Recognitioncited by 98
  35. 2021The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usagecited by 98
  36. 2015Multi-task Sequence to Sequence Learningcited by 94
  37. 2021BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognitioncited by 88
  38. 2017Multilingual Speech Recognition With A Single End-To-End Modelcited by 87

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 10; 2023: 497; 2024: 937; 2025: 1330; 2026: 1198.

3,972 papers.

Sort:

By area:

  1. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  2. 2023MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilitiescited by 1,221
  3. 2022Reproducible scaling laws for contrastive language-image learningcited by 1,163
  4. 2023VideoChat: Chat-Centric Video Understandingcited by 851
  5. 2023On-Policy Distillation of Language Models: Learning from Self-Generated Mistakescited by 840
  6. 2025Qwen2.5-Omni Technical Reportcited by 704
  7. 2023A Watermark for Large Language Modelscited by 667
  8. 2023A Comprehensive Overview of Large Language Modelscited by 639
  9. 2023DataComp: In search of the next generation of multimodal datasetscited by 635
  10. 2023Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Modelscited by 591
  11. 2024Qwen2-Audio Technical Reportcited by 543
  12. 2024Moshi: a speech-text foundation model for real-time dialoguecited by 536
38 more
  1. 2023SALMONN: Towards Generic Hearing Abilities for Large Language Modelscited by 492
  2. 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 477
  3. 2023Scaling Speech Technology to 1,000+ Languagescited by 401
  4. 2023TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understandingcited by 399
  5. 2023Hyena Hierarchy: Towards Larger Convolutional Language Modelscited by 388
  6. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 373
  7. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 353
  8. 2023AudioPaLM: A Large Language Model That Can Speak and Listencited by 333
  9. 2024InternVideo2: Scaling Foundation Models for Multimodal Video Understandingcited by 310
  10. 2023Photorealistic Video Generation with Diffusion Modelscited by 304
  11. 2024OLMoE: Open Mixture-of-Experts Language Modelscited by 291
  12. 2024CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Modelscited by 282
  13. 2024MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmarkcited by 281
  14. 2024MM-LLMs: Recent Advances in MultiModal Large Language Modelscited by 277
  15. 2023Poisoning Web-Scale Training Datasets is Practicalcited by 276
  16. 2023AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Headcited by 264
  17. 2023Provable Robust Watermarking for AI-Generated Textcited by 259
  18. 2023Challenges and Applications of Large Language Modelscited by 251
  19. 2023Data Filtering Networkscited by 247
  20. 2023Google USM: Scaling Automatic Speech Recognition Beyond 100 Languagescited by 228
  21. 2025Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Modelscited by 216
  22. 2024AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehensioncited by 215
  23. 2024AnyGPT: Unified Multimodal LLM with Discrete Sequence Modelingcited by 213
  24. 2025Kimi-Audio Technical Reportcited by 210
  25. 2023On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspectivecited by 208
  26. 2024Mini-Omni: Language Models Can Hear, Talk While Thinking in Streamingcited by 204
  27. 2023Video Understanding with Large Language Models: A Surveycited by 203
  28. 2024LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Controlcited by 202
  29. 2024NaVILA: Legged Robot Vision-Language-Action Model for Navigationcited by 201
  30. 2024Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generationcited by 200
  31. 2023emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representationcited by 196
  32. 2024InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Outputcited by 195
  33. 2023Quilt-1M: One Million Image-Text Pairs for Histopathologycited by 192
  34. 2024VoiceBench: Benchmarking LLM-Based Voice Assistantscited by 192
  35. 2023TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIscited by 184
  36. 2024Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilitiescited by 183
  37. 2024XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Modelcited by 174
  38. 2023On the Reliability of Watermarks for Large Language Modelscited by 170

50 most cited of 3,972 All 3,972 (JSON)