# A Practitioner's Guide to Building ASR Models for Low-Resource Languages: A Case Study on Scottish Gaelic

arXiv: https://arxiv.org/abs/2506.04915 · HTML: https://mlsanity.com/paper/2506.04915/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 40 references that are in the map.
- First posted on arXiv 5 Jun 2025.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale](https://mlsanity.com/paper/2406.17557/) (2024)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [MADLAD-400: A Multilingual And Document-Level Large Audited Dataset](https://mlsanity.com/paper/2309.04662/) (2023)
- [LLaMA-Omni: Seamless Speech Interaction with Large Language Models](https://mlsanity.com/paper/2409.06666/) (2024)
- [Improved Noisy Student Training for Automatic Speech Recognition](https://mlsanity.com/paper/2005.09629/) (2020)
- [Self-training and Pre-training are Complementary for Speech Recognition](https://mlsanity.com/paper/2010.11430/) (2020)
- [Towards Robust Speech Representation Learning for Thousands of Languages](https://mlsanity.com/paper/2407.00837/) (2024)
- [HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models](https://mlsanity.com/paper/2309.15701/) (2023)
- [Latxa: An Open Language Model and Evaluation Suite for Basque](https://mlsanity.com/paper/2403.20266/) (2024)
- [From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition](https://mlsanity.com/paper/1910.01493/) (2019)
- [Active and Semi-Supervised Learning in ASR: Benefits on the Acoustic and Language Models](https://mlsanity.com/paper/1903.02852/) (2019)
- [Cross-lingual Knowledge Transfer and Iterative Pseudo-labeling for Low-Resource Speech Recognition with Transducers](https://mlsanity.com/paper/2305.13652/) (2023)

## Built on by (most cited first, 5 of 5)

- [How I Built ASR for Endangered Languages with a Spoken Dictionary](https://mlsanity.com/paper/2510.04832/) (2025)
- [BlasBench: An Open Benchmark for Irish Speech Recognition](https://mlsanity.com/paper/2604.10736/) (2026)
- [A Modular Part-of-Speech Tagger for Scottish Gaelic using spaCy](https://mlsanity.com/paper/2608.04808/) (2026)
- [T-SANDHI: Tone Sandhi-aware Adaptive Network with Decoupled Hybrid Injection for Low-resource Taiwanese Hokkien Speech Recognition](https://mlsanity.com/paper/2609.18194/) (2026)
- [NADI 2026: The Second Multidialectal Arabic Speech Processing Shared Task](https://mlsanity.com/paper/2609.27086/) (2026)

## Abstract (arXiv)

An effective approach to the development of ASR systems for low-resource languages is to fine-tune an existing multilingual end-to-end model. When the original model has been trained on large quantities of data from many languages, fine-tuning can be effective with limited training data, even when the language in question was not present in the original training data. The fine-tuning approach has been encouraged by the availability of public-domain E2E models and is widely believed to lead to state-of-the-art results. This paper, however, challenges that belief. We show that an approach combining hybrid HMMs with self-supervised models can yield substantially better performance with limited training data. This combination allows better utilisation of all available speech and text data through continued self-supervised pre-training and semi-supervised training. We benchmark our approach on Scottish Gaelic, achieving WER reductions of 32% relative over our best fine-tuned Whisper model.