# Improving low-resource ASR using bilingual fine-tuning with language identification: a cross-linguistic evaluation

arXiv: https://arxiv.org/abs/2606.17820 · HTML: https://mlsanity.com/paper/2606.17820/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 15 references that are in the map.
- First posted on arXiv 16 Jun 2026.

## Builds on (most cited first, 11 of 11)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [Adapt-and-Adjust: Overcoming the Long-Tail Problem of Multilingual Speech Recognition](https://mlsanity.com/paper/2012.01687/) (2020)
- [Improving Massively Multilingual ASR With Auxiliary CTC Objectives](https://mlsanity.com/paper/2302.12829/) (2023)
- [Meta Learning for End-to-End Low-Resource Speech Recognition](https://mlsanity.com/paper/1910.12094/) (2019)
- [Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognition](https://mlsanity.com/paper/2012.11896/) (2020)
- [Adapting Monolingual Models: Data can be Scarce when Language Similarity is High](https://mlsanity.com/paper/2105.02855/) (2021)
- [Learning ASR pathways: A sparse multilingual ASR model](https://mlsanity.com/paper/2209.05735/) (2022)
- [Hierarchical Softmax for End-to-End Low-resource Multilingual Speech Recognition](https://mlsanity.com/paper/2204.03855/) (2022)
- [Evaluating Standard and Dialectal Frisian ASR: Multilingual Fine-tuning and Language Identification for Improved Low-resource Performance](https://mlsanity.com/paper/2502.04883/) (2025)

## Abstract (arXiv)

This study explores how bilingual fine-tuning affects automatic speech recognition (ASR) in low-resource languages. We evaluate this method across nine linguistically and geographically diverse language pairs, covering a range of language families and writing systems. To distinguish the two languages, during training, we pre-pend each input text with a language identification token. At inference, the model jointly predicts both the language and transcription from the speech input alone. As texts for which the language is incorrectly determined show low ASR performance, we also conduct a follow-up experiment in which the language identification token is provided both during training and inference. Our results show that bilingual fine-tuning can be beneficial when language identification accuracy is high, and that in cases where language identification performance is low, including the language identification token at inference helps to improve ASR performance.