# Breaking the Transcription Bottleneck: Fine-tuning ASR Models for Extremely Low-Resource Fieldwork Languages

arXiv: https://arxiv.org/abs/2506.17459 · HTML: https://mlsanity.com/paper/2506.17459/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 61 references that are in the map.
- First posted on arXiv 20 Jun 2025.

## Builds on (most cited first, 21 of 21)

- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [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)
- [WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition](https://mlsanity.com/paper/2110.03370/) (2021)
- [Unsupervised Speech Recognition](https://mlsanity.com/paper/2105.11084/) (2021)
- [The Zero Resource Speech Challenge 2019: TTS without T](https://mlsanity.com/paper/1904.11469/) (2019)
- [Adapting Multilingual Speech Representation Model for a New, Underresourced Language through Multilingual Fine-tuning and Continued Pretraining](https://mlsanity.com/paper/2301.07295/) (2023)
- [End-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representation](https://mlsanity.com/paper/2204.00540/) (2022)
- [Leveraging End-to-End ASR for Endangered Language Documentation: An Empirical Study on Yolox'ochitl Mixtec](https://mlsanity.com/paper/2101.10877/) (2021)
- [BembaSpeech: A Speech Recognition Corpus for the Bemba Language](https://mlsanity.com/paper/2102.04889/) (2021)
- [Open Source Automatic Speech Recognition for German](https://mlsanity.com/paper/1807.10311/) (2018)
- [Investigating data partitioning strategies for crosslinguistic low-resource ASR evaluation](https://mlsanity.com/paper/2208.12888/) (2022)
- [Improving Low-Resource Speech Recognition with Pretrained Speech Models: Continued Pretraining vs. Semi-Supervised Training](https://mlsanity.com/paper/2207.00659/) (2022)
- [Leveraging translations for speech transcription in low-resource settings](https://mlsanity.com/paper/1803.08991/) (2018)
- [User-friendly automatic transcription of low-resource languages: Plugging ESPnet into Elpis](https://mlsanity.com/paper/2101.03027/) (2020)
- [Efficient Adapter Finetuning for Tail Languages in Streaming Multilingual ASR](https://mlsanity.com/paper/2401.08992/) (2024)
- [Continued Pretraining for Domain Adaptation of Wav2vec2.0 in Automatic Speech Recognition for Elementary Math Classroom Settings](https://mlsanity.com/paper/2405.13018/) (2024)
- [Semi-supervised transfer learning for language expansion of end-to-end speech recognition models to low-resource languages](https://mlsanity.com/paper/2111.10047/) (2021)

## Built on by (most cited first, 3 of 3)

- [Hard to Be Heard: Phoneme-Level ASR Analysis of Phonologically Complex, Low-Resource Endangered Languages](https://mlsanity.com/paper/2604.18204/) (2026)
- [Balalaika: Data-Centric, Prosody-Aware Annotation Pipeline for Russian Speech](https://mlsanity.com/paper/2507.13563/) (2025)
- [Automatic Speech Recognition for Documenting Endangered Languages: Case Study of Ikema Miyakoan](https://mlsanity.com/paper/2603.26248/) (2026)

## Abstract (arXiv)

Automatic Speech Recognition (ASR) has reached impressive accuracy for high-resource languages, yet its utility in linguistic fieldwork remains limited. Recordings collected in fieldwork contexts present unique challenges, including spontaneous speech, environmental noise, and severely constrained datasets from under-documented languages. In this paper, we benchmark the performance of two fine-tuned multilingual ASR models, MMS and XLS-R, on five typologically diverse low-resource languages with control of training data duration. Our findings show that MMS is best suited when extremely small amounts of training data are available, whereas XLS-R shows parity performance once training data exceed one hour. We provide linguistically grounded analysis for further provide insights towards practical guidelines for field linguists, highlighting reproducible ASR adaptation approaches to mitigate the transcription bottleneck in language documentation.