# How I Built ASR for Endangered Languages with a Spoken Dictionary

arXiv: https://arxiv.org/abs/2510.04832 · HTML: https://mlsanity.com/paper/2510.04832/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 31 references that are in the map.
- First posted on arXiv 6 Oct 2025.

## Builds on (most cited first, 17 of 17)

- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling](https://mlsanity.com/paper/2303.03926/) (2023)
- [Unsupervised Speech Recognition](https://mlsanity.com/paper/2105.11084/) (2021)
- [A Benchmark for Learning to Translate a New Language from One Grammar Book](https://mlsanity.com/paper/2309.16575/) (2023)
- [A Comparison of Techniques for Language Model Integration in Encoder-Decoder Speech Recognition](https://mlsanity.com/paper/1807.10857/) (2018)
- [Towards End-to-end Unsupervised Speech Recognition](https://mlsanity.com/paper/2204.02492/) (2022)
- [Comparison of Multilingual Self-Supervised and Weakly-Supervised Speech Pre-Training for Adaptation to Unseen Languages](https://mlsanity.com/paper/2305.12606/) (2023)
- [Bilingual Dictionary Based Neural Machine Translation without Using Parallel Sentences](https://mlsanity.com/paper/2007.02671/) (2020)
- [A Crowdsourced Open-Source Kazakh Speech Corpus and Initial Speech Recognition Baseline](https://mlsanity.com/paper/2009.10334/) (2020)
- [CAT: A CTC-CRF based ASR Toolkit Bridging the Hybrid and the End-to-end Approaches towards Data Efficiency and Low Latency](https://mlsanity.com/paper/2005.13326/) (2020)
- [A Practitioner's Guide to Building ASR Models for Low-Resource Languages: A Case Study on Scottish Gaelic](https://mlsanity.com/paper/2506.04915/) (2025)
- [The ML-SUPERB 2.0 Challenge: Towards Inclusive ASR Benchmarking for All Language Varieties](https://mlsanity.com/paper/2509.07139/) (2025)
- [Speech Corpus of Ainu Folklore and End-to-end Speech Recognition for Ainu Language](https://mlsanity.com/paper/2002.06675/) (2020)
- [Look It Up: Bilingual Dictionaries Improve Neural Machine Translation](https://mlsanity.com/paper/2010.05997/) (2020)

## Built on by (most cited first, 1 of 1)

- [BlasBench: An Open Benchmark for Irish Speech Recognition](https://mlsanity.com/paper/2604.10736/) (2026)

## Abstract (arXiv)

Nearly half of the world's languages are endangered. Speech technologies such as Automatic Speech Recognition (ASR) are central to revival efforts, yet most languages remain unsupported because standard pipelines expect utterance-level supervised data. Speech data often exist for endangered languages but rarely match these formats. Manx Gaelic (~2,200 speakers), for example, has had transcribed speech since 1948, yet remains unsupported by modern systems. In this paper, we explore how little data, and in what form, is needed to build ASR for critically endangered languages. We show that a short-form pronunciation resource is a viable alternative, and that 40 minutes of such data produces usable ASR for Manx (<50% WER). We replicate our approach, applying it to Cornish (~600 speakers), another critically endangered language. Results show that the barrier to entry, in quantity and form, is far lower than previously thought, giving hope to endangered language communities that cannot afford to meet the requirements arbitrarily imposed upon them.