mlsanityData to 7 Oct 2026

Pseudo-Labeling for Massively Multilingual Speech Recognition

arXiv 2111.00161 ↗First posted 30 Oct 2021cs.CL cs.SD eess.AScited by 23

Not on the map. Why?

Abstract (arXiv)

Semi-supervised learning through pseudo-labeling has become a staple of state-of-the-art monolingual speech recognition systems. In this work, we extend pseudo-labeling to massively multilingual speech recognition with 60 languages. We propose a simple pseudo-labeling recipe that works well even with low-resource languages: train a supervised multilingual model, fine-tune it with semi-supervised learning on a target language, generate pseudo-labels for that language, and train a final model using pseudo-labels for all languages, either from scratch or by fine-tuning. Experiments on the labeled Common Voice and unlabeled VoxPopuli datasets show that our recipe can yield a model with better performance for many languages that also transfers well to LibriSpeech.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 28 of its 38 references that are in the map. First posted on arXiv 30 Oct 2021.

Builds on

28 of 38 references.

References · 28

  1. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  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. 2018Self-Attention with Relative Position Representationscited by 1,112
  5. 2015Listen, Attend and Spellcited by 542
  6. 2020Unsupervised Cross-lingual Representation Learning for Speech Recognitioncited by 496
  7. 2021VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretationcited by 455
  8. 2015Attention-Based Models for Speech Recognitioncited by 400
  9. 2018Streaming End-to-end Speech Recognition For Mobile Devicescited by 230
  10. 2020Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognitioncited by 185
  11. 2020Improved Noisy Student Training for Automatic Speech Recognitioncited by 139
  12. 2019Self-Training for End-to-End Speech Recognitioncited by 128
16 more
  1. 2019End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architecturescited by 120
  2. 2020Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameterscited by 110
  3. 2020Self-training and Pre-training are Complementary for Speech Recognitioncited by 98
  4. 2019Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Modelcited by 92
  5. 2017Multilingual Speech Recognition With A Single End-To-End Modelcited by 87
  6. 2021Multi-Task Self-Training for Learning General Representationscited by 85
  7. 2020Iterative Pseudo-Labeling for Speech Recognitioncited by 81
  8. 2020Rethinking Evaluation in ASR: Are Our Models Robust Enough?cited by 72
  9. 2018Bytes are All You Need: End-to-End Multilingual Speech Recognition and Synthesis with Bytescited by 54
  10. 2020SlimIPL: Language-Model-Free Iterative Pseudo-Labelingcited by 54
  11. 2021CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddingscited by 47
  12. 2021Momentum Pseudo-Labeling for Semi-Supervised Speech Recognitioncited by 37
  13. 2018Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modelingcited by 34
  14. 2019Massively Multilingual Adversarial Speech Recognitioncited by 28
  15. 2020RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutionscited by 26
  16. 2017Phonemic and Graphemic Multilingual CTC Based Speech Recognitioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 7; 2024: 5; 2025: 3; 2026: 4.

23 papers.

Sort:

  1. 2023Scaling Speech Technology to 1,000+ Languagescited by 401
  2. 2024GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinementcited by 34
  3. 2023Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentationcited by 30
  4. 2023Comparison of Multilingual Self-Supervised and Weakly-Supervised Speech Pre-Training for Adaptation to Unseen Languagescited by 20
  5. 2023CL-MASR: A Continual Learning Benchmark for Multilingual ASRcited by 16
  6. 2022Towards Zero-Shot Code-Switched Speech Recognitioncited by 15
  7. 2022Boosting Cross-Domain Speech Recognition with Self-Supervisioncited by 10
  8. 2023A Novel Self-training Approach for Low-resource Speech Recognitioncited by 7
  9. 2022Optimizing Bilingual Neural Transducer with Synthetic Code-switching Text Generationcited by 5
  10. 2023Optimizing Two-Pass Cross-Lingual Transfer Learning: Phoneme Recognition and Phoneme to Grapheme Translationcited by 5
  11. 2024Empowering Low-Resource Language ASR via Large-Scale Pseudo Labelingcited by 4
  12. 2025Efficient Data Selection for Domain Adaptation of ASR Using Pseudo-Labels and Multi-Stage Filteringcited by 3
11 more
  1. 2024Token-Weighted RNN-T for Learning from Flawed Datacited by 2
  2. 2025NIRANTAR: Continual Learning with New Languages and Domains on Real-world Speech Datacited by 2
  3. 2022Watch What You Pretrain For: Targeted, Transferable Adversarial Examples on Self-Supervised Speech Recognition modelscited by 1
  4. 2024ManWav: The First Manchu ASR Modelcited by 1
  5. 2024Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whispercited by 1
  6. 2023Unsupervised ASR via Cross-Lingual Pseudo-Labelingcited by 0
  7. 2025Unified Acoustic Representations for Screening Neurological and Respiratory Pathologies from Voicecited by 0
  8. 2026Speak in Context: Multilingual ASR with Speech Context Alignment via Contrastive Learningcited by 0
  9. 2026WorldSpeech: A Multilingual Speech Corpus from Around the Worldcited by 0
  10. 2026The Exact Worst-Case Tail Probability under Bounded Kurtosiscited by 0
  11. 2026Look Less, Hear Better: Jointly Rewarded GRPO for Streaming ASRcited by 0