# Towards dialect-inclusive recognition in a low-resource language: are balanced corpora the answer?

arXiv: https://arxiv.org/abs/2307.07295 · HTML: https://mlsanity.com/paper/2307.07295/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 37 references that are in the map.
- First posted on arXiv 14 Jul 2023.

## Builds on (most cited first, 6 of 6)

- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [Quantifying Bias in Automatic Speech Recognition](https://mlsanity.com/paper/2103.15122/) (2021)
- [Multi-Dialect Speech Recognition With A Single Sequence-To-Sequence Model](https://mlsanity.com/paper/1712.01541/) (2017)
- [Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition](https://mlsanity.com/paper/1802.02656/) (2018)
- [Integrating Categorical Features in End-to-End ASR](https://mlsanity.com/paper/2110.03047/) (2021)

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

- [Can Whisper perform speech-based in-context learning?](https://mlsanity.com/paper/2309.07081/) (2023)
- [Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs](https://mlsanity.com/paper/2512.16378/) (2025)
- [Low-resource speech recognition and dialect identification of Irish in a multi-task framework](https://mlsanity.com/paper/2405.01293/) (2024)
- [Standard-to-Dialect Transfer Trends Differ across Text and Speech: A Case Study on Intent and Topic Classification in German Dialects](https://mlsanity.com/paper/2510.07890/) (2025)
- [Fotheidil: an Automatic Transcription System for the Irish Language](https://mlsanity.com/paper/2501.00509/) (2024)

## Abstract (arXiv)

ASR systems are generally built for the spoken 'standard', and their performance declines for non-standard dialects/varieties. This is a problem for a language like Irish, where there is no single spoken standard, but rather three major dialects: Ulster (Ul), Connacht (Co) and Munster (Mu). As a diagnostic to quantify the effect of the speaker's dialect on recognition performance, 12 ASR systems were trained, firstly using baseline dialect-balanced training corpora, and then using modified versions of the baseline corpora, where dialect-specific materials were either subtracted or added. Results indicate that dialect-balanced corpora do not yield a similar performance across the dialects: the Ul dialect consistently underperforms, whereas Mu yields lowest WERs. There is a close relationship between Co and Mu dialects, but one that is not symmetrical. These results will guide future corpus collection and system building strategies to optimise for cross-dialect performance equity.