mlsanityData to 7 Oct 2026

Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameters

arXiv 2007.03001 ↗First posted 6 Jul 2020eess.AS cs.CL cs.SDcited by 110

Not on the map. Why?

Abstract (arXiv)

We study training a single acoustic model for multiple languages with the aim of improving automatic speech recognition (ASR) performance on low-resource languages, and over-all simplifying deployment of ASR systems that support diverse languages. We perform an extensive benchmark on 51 languages, with varying amount of training data by language(from 100 hours to 1100 hours). We compare three variants of multilingual training from a single joint model without knowing the input language, to using this information, to multiple heads (one per language cluster). We show that multilingual training of ASR models on several languages can improve recognition performance, in particular, on low resource languages. We see 20.9%, 23% and 28.8% average WER relative reduction compared to monolingual baselines on joint model, joint model with language input and multi head model respectively. To our knowledge, this is the first work studying multilingual ASR at massive scale, with more than 50 languages and more than 16,000 hours of audio across them.

Key facts. Cited by 110 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 25; 2022: 23; 2023: 27; 2024: 21; 2025: 8; 2026: 6.

110 papers.

Sort:

By area:

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  2. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  3. 2022A Generalist Agentcited by 802
  4. 2023Scaling Speech Technology to 1,000+ Languagescited by 401
  5. 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 138
  6. 2023End-to-End Speech Recognition: A Surveycited by 127
  7. 2021Simple and Effective Zero-shot Cross-lingual Phoneme Recognitioncited by 79
  8. 2021Scaling End-to-End Models for Large-Scale Multilingual ASRcited by 61
  9. 2021Multilingual and code-switching ASR challenges for low resource Indian languagescited by 50
  10. 2021PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognitioncited by 50
  11. 2021Towards One Model to Rule All: Multilingual Strategy for Dialectal Code-Switching Arabic ASRcited by 40
  12. 2022u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modalitycited by 36
38 more
  1. 2021Multilingual and Cross-Lingual Intent Detection from Spoken Datacited by 35
  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. 2021Exploiting Adapters for Cross-lingual Low-resource Speech Recognitioncited by 33
  4. 2023Improving Massively Multilingual ASR With Auxiliary CTC Objectivescited by 31
  5. 2023Large Language Model Instruction Following: A Survey of Progresses and Challengescited by 31
  6. 2021A Configurable Multilingual Model is All You Need to Recognize All Languagescited by 28
  7. 2024ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasetscited by 26
  8. 2022Streaming End-to-End Multilingual Speech Recognition with Joint Language Identificationcited by 24
  9. 2021Pseudo-Labeling for Massively Multilingual Speech Recognitioncited by 23
  10. 2022A Survey of Multilingual Models for Automatic Speech Recognitioncited by 21
  11. 2022LAE: Language-Aware Encoder for Monolingual and Multilingual ASRcited by 21
  12. 2021Improved Language Identification Through Cross-Lingual Self-Supervised Learningcited by 20
  13. 2023Comparison of Multilingual Self-Supervised and Weakly-Supervised Speech Pre-Training for Adaptation to Unseen Languagescited by 20
  14. 2021Joint Modeling of Code-Switched and Monolingual ASR via Conditional Factorizationcited by 17
  15. 2023Mixture-of-Expert Conformer for Streaming Multilingual ASRcited by 17
  16. 2024Whistle: Data-Efficient Multilingual and Crosslingual Speech Recognition via Weakly Phonetic Supervisioncited by 17
  17. 2021Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systemscited by 16
  18. 2022Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilitiescited by 16
  19. 2025Scaling Analysis of Interleaved Speech-Text Language Modelscited by 13
  20. 2021Efficient Weight factorization for Multilingual Speech Recognitioncited by 12
  21. 2022Learning ASR pathways: A sparse multilingual ASR modelcited by 12
  22. 2023MD3: The Multi-Dialect Dataset of Dialoguescited by 12
  23. 2024Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Studycited by 12
  24. 2022Combining Spectral and Self-Supervised Features for Low Resource Speech Recognition and Translationcited by 11
  25. 2021Differentiable Allophone Graphs for Language-Universal Speech Recognitioncited by 10
  26. 2022CLEAR: Improving Vision-Language Navigation with Cross-Lingual, Environment-Agnostic Representationscited by 10
  27. 2023Findings of the 2023 ML-SUPERB Challenge: Pre-Training and Evaluation over More Languages and Beyondcited by 10
  28. 2022Adaptive multilingual speech recognition with pretrained modelscited by 9
  29. 2022A Language Agnostic Multilingual Streaming On-Device ASR Systemcited by 9
  30. 2023Master-ASR: Achieving Multilingual Scalability and Low-Resource Adaptation in ASR with Modular Learningcited by 9
  31. 2021Cross-lingual Transfer for Speech Processing using Acoustic Language Similaritycited by 8
  32. 2023Unified model for code-switching speech recognition and language identification based on a concatenated tokenizercited by 8
  33. 2022Language technology practitioners as language managers: arbitrating data bias and predictive bias in ASRcited by 7
  34. 2022Distilling a Pretrained Language Model to a Multilingual ASR Modelcited by 7
  35. 2022Scaling Up Deliberation for Multilingual ASRcited by 6
  36. 2024Exploring SSL Discrete Tokens for Multilingual ASRcited by 6
  37. 2021SpeakerStew: Scaling to Many Languages with a Triaged Multilingual Text-Dependent and Text-Independent Speaker Verification Systemcited by 5
  38. 2021Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modelingcited by 5

50 most cited of 110 All 110 (JSON)