mlsanityData to 14 Oct 2026

Scaling A Simple Approach to Zero-Shot Speech Recognition

arXiv 2407.17852 ↗First posted 25 Jul 2024cs.CLcited by 8

Not on the map. Why?

Abstract (arXiv)

Despite rapid progress in increasing the language coverage of automatic speech recognition, the field is still far from covering all languages with a known writing script. Recent work showed promising results with a zero-shot approach requiring only a small amount of text data, however, accuracy heavily depends on the quality of the used phonemizer which is often weak for unseen languages. In this paper, we present MMS Zero-shot a conceptually simpler approach based on romanization and an acoustic model trained on data in 1,078 different languages or three orders of magnitude more than prior art. MMS Zero-shot reduces the average character error rate by a relative 46% over 100 unseen languages compared to the best previous work. Moreover, the error rate of our approach is only 2.5x higher compared to in-domain supervised baselines, while our approach uses no labeled data for the evaluation languages at all.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 20 of its 31 references that are in the map. First posted on arXiv 25 Jul 2024.

Builds on

20 of 31 references.

References · 20

  1. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  2. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  3. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  4. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  5. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
  6. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
  7. 2020Unsupervised Cross-lingual Representation Learning for Speech Recognitioncited by 501
  8. 2022FLEURS: Few-shot Learning Evaluation of Universal Representations of Speechcited by 469
  9. 2023Scaling Speech Technology to 1,000+ Languagescited by 411
  10. 2023Google USM: Scaling Automatic Speech Recognition Beyond 100 Languagescited by 231
  11. 2021Unsupervised Speech Recognitioncited by 148
  12. 2019Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Modelcited by 93
8 more
  1. 2020Universal Phone Recognition with a Multilingual Allophone Systemcited by 81
  2. 2018wav2letter++: The Fastest Open-source Speech Recognition Systemcited by 42
  3. 2018Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modelingcited by 34
  4. 2022ASR2K: Speech Recognition for Around 2000 Languages without Audiocited by 26
  5. 2019VQVAE Unsupervised Unit Discovery and Multi-scale Code2Spec Inverter for Zerospeech Challenge 2019cited by 25
  6. 2022Flashlight: Enabling Innovation in Tools for Machine Learningcited by 25
  7. 2018Completely Unsupervised Phoneme Recognition by Adversarially Learning Mapping Relationships from Audio Embeddingscited by 22
  8. 2020AlloVera: A Multilingual Allophone Databasecited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 4; 2026: 1.

8 papers.

  1. 2025CS-FLEURS: A Massively Multilingual and Code-Switched Speech Datasetcited by 12
  2. 2025Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representationscited by 9
  3. 2024SpeechTaxi: On Multilingual Semantic Speech Classificationcited by 6
  4. 2024LAMA-UT: Language Agnostic Multilingual ASR through Orthography Unification and Language-Specific Transliterationcited by 3
  5. 2024Improving Multilingual ASR in the Wild Using Simple N-best Re-rankingcited by 2
  6. 2025TalTech Systems for the Interspeech 2025 ML-SUPERB 2.0 Challengecited by 1
  7. 2025MLMA: Towards Multilingual ASR With Mamba-based Architecturescited by 1
  8. 2026Kakugo: Distillation of Low-Resource Languages into Small Language Modelscited by 1