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

arXiv: https://arxiv.org/abs/2603.18612 · HTML: https://mlsanity.com/paper/2603.18612/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 38 references that are in the map.
- First posted on arXiv 19 Mar 2026.

## Builds on (most cited first, 22 of 22)

- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation](https://mlsanity.com/paper/2101.00390/) (2021)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [Generative Spoken Language Modeling from Raw Audio](https://mlsanity.com/paper/2102.01192/) (2021)
- [Spirit LM: Interleaved Spoken and Written Language Model](https://mlsanity.com/paper/2402.05755/) (2024)
- [The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling](https://mlsanity.com/paper/2011.11588/) (2020)
- [EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis](https://mlsanity.com/paper/2308.05725/) (2023)
- [ML-SUPERB: Multilingual Speech Universal PERformance Benchmark](https://mlsanity.com/paper/2305.10615/) (2023)
- [Self-Supervised Speech Representations are More Phonetic than Semantic](https://mlsanity.com/paper/2406.08619/) (2024)
- [Towards Robust Speech Representation Learning for Thousands of Languages](https://mlsanity.com/paper/2407.00837/) (2024)
- [The Zero Resource Speech Challenge 2021: Spoken language modelling](https://mlsanity.com/paper/2104.14700/) (2021)
- [The Zero Resource Speech Challenge 2017](https://mlsanity.com/paper/1712.04313/) (2017)
- [Self-supervised language learning from raw audio: Lessons from the Zero Resource Speech Challenge](https://mlsanity.com/paper/2210.15759/) (2022)
- [Probing phoneme, language and speaker information in unsupervised speech representations](https://mlsanity.com/paper/2203.16193/) (2022)
- [Word Segmentation on Discovered Phone Units with Dynamic Programming and Self-Supervised Scoring](https://mlsanity.com/paper/2202.11929/) (2022)
- [Estimating the Completeness of Discrete Speech Units](https://mlsanity.com/paper/2409.06109/) (2024)
- [Unsupervised word segmentation and lexicon discovery using acoustic word embeddings](https://mlsanity.com/paper/1603.02845/) (2016)
- [Improving Spoken Language Modeling with Phoneme Classification: A Simple Fine-tuning Approach](https://mlsanity.com/paper/2410.00025/) (2024)
- [SpidR: Learning Fast and Stable Linguistic Units for Spoken Language Models Without Supervision](https://mlsanity.com/paper/2512.20308/) (2025)
- [fastabx: A library for efficient computation of ABX discriminability](https://mlsanity.com/paper/2505.02692/) (2025)

## 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.