mlsanityData to 7 Oct 2026

DiscoPhon: Benchmarking the Unsupervised Discovery of Phoneme Inventories With Discrete Speech Units

arXiv 2603.18612 ↗First posted 19 Mar 2026cs.CL cs.SD eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce DiscoPhon, a multilingual benchmark for evaluating unsupervised phoneme discovery from discrete speech units. DiscoPhon covers 6 dev and 6 test languages, chosen to span a wide range of phonemic contrasts. Given only 10 hours of speech in a previously unseen language, systems must produce discrete units that are mapped to a predefined phoneme inventory, through either a many-to-one or a one-to-one assignment. The resulting sequences are evaluated for unit quality, recognition and segmentation. We provide four pretrained multilingual HuBERT and SpidR baselines, and show that phonemic information is available enough in current models for derived units to correlate well with phonemes, though with variations across languages.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 38 references that are in the map. First posted on arXiv 19 Mar 2026.

Builds on

22 of 38 references.

References · 22

  1. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  2. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  3. 2022AudioLM: a Language Modeling Approach to Audio Generationcited by 611
  4. 2021VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretationcited by 455
  5. 2023Scaling Speech Technology to 1,000+ Languagescited by 401
  6. 2021Generative Spoken Language Modeling from Raw Audiocited by 336
  7. 2024Spirit LM: Interleaved Spoken and Written Language Modelcited by 123
  8. 2020The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modelingcited by 100
  9. 2023EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesiscited by 93
  10. 2023ML-SUPERB: Multilingual Speech Universal PERformance Benchmarkcited by 70
  11. 2024Self-Supervised Speech Representations are More Phonetic than Semanticcited by 70
  12. 2024Towards Robust Speech Representation Learning for Thousands of Languagescited by 48
10 more
  1. 2021The Zero Resource Speech Challenge 2021: Spoken language modellingcited by 47
  2. 2017The Zero Resource Speech Challenge 2017cited by 45
  3. 2022Self-supervised language learning from raw audio: Lessons from the Zero Resource Speech Challengecited by 34
  4. 2022Probing phoneme, language and speaker information in unsupervised speech representationscited by 31
  5. 2022Word Segmentation on Discovered Phone Units with Dynamic Programming and Self-Supervised Scoringcited by 24
  6. 2024Estimating the Completeness of Discrete Speech Unitscited by 9
  7. 2016Unsupervised word segmentation and lexicon discovery using acoustic word embeddingscited by 8
  8. 2024Improving Spoken Language Modeling with Phoneme Classification: A Simple Fine-tuning Approachcited by 8
  9. 2025fastabx: A library for efficient computation of ABX discriminabilitycited by 7
  10. 2025SpidR: Learning Fast and Stable Linguistic Units for Spoken Language Models Without Supervisioncited by 6

Built on by

Not cited yet.