# Automatic Speech Recognition Advancements for Indigenous Languages of the Americas

arXiv: https://arxiv.org/abs/2404.08368 · HTML: https://mlsanity.com/paper/2404.08368/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 83 references that are in the map.
- First posted on arXiv 12 Apr 2024.

## Builds on (most cited first, 23 of 23)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation](https://mlsanity.com/paper/2101.00390/) (2021)
- [Unsupervised Speech Recognition](https://mlsanity.com/paper/2105.11084/) (2021)
- [VoxLingua107: a Dataset for Spoken Language Recognition](https://mlsanity.com/paper/2011.12998/) (2020)
- [End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures](https://mlsanity.com/paper/1911.08460/) (2019)
- [Iterative Pseudo-Labeling for Speech Recognition](https://mlsanity.com/paper/2005.09267/) (2020)
- [Transfer Learning for Speech and Language Processing](https://mlsanity.com/paper/1511.06066/) (2015)
- [Applying Wav2vec2.0 to Speech Recognition in Various Low-resource Languages](https://mlsanity.com/paper/2012.12121/) (2020)
- [Challenges of language technologies for the indigenous languages of the Americas](https://mlsanity.com/paper/1806.04291/) (2018)
- [Massively Multilingual Adversarial Speech Recognition](https://mlsanity.com/paper/1904.02210/) (2019)
- [Transfer Learning for Speech Recognition on a Budget](https://mlsanity.com/paper/1706.00290/) (2017)
- [Data Augmentation for Low-Resource Quechua ASR Improvement](https://mlsanity.com/paper/2207.06872/) (2022)
- [Master-ASR: Achieving Multilingual Scalability and Low-Resource Adaptation in ASR with Modular Learning](https://mlsanity.com/paper/2306.15686/) (2023)
- [Leveraging ASR Pretrained Conformers for Speaker Verification through Transfer Learning and Knowledge Distillation](https://mlsanity.com/paper/2309.03019/) (2023)
- [Evaluating Self-Supervised Speech Representations for Indigenous American Languages](https://mlsanity.com/paper/2310.03639/) (2023)
- [A New Benchmark of Aphasia Speech Recognition and Detection Based on E-Branchformer and Multi-task Learning](https://mlsanity.com/paper/2305.13331/) (2023)

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

- [Giving Voice to the Constitution: Low-Resource Text-to-Speech for Quechua and Spanish Using a Bilingual Legal Corpus](https://mlsanity.com/paper/2604.13288/) (2026)

## Abstract (arXiv)

Indigenous languages are a fundamental legacy in the development of human communication, embodying the unique identity and culture of local communities in America. The Second AmericasNLP (Americas Natural Language Processing) Competition Track 1 of NeurIPS (Neural Information Processing Systems) 2022 proposed the task of training automatic speech recognition (ASR) systems for five Indigenous languages: Quechua, Guarani, Bribri, Kotiria, and Wa'ikhana. In this paper, we describe the fine-tuning of a state-of-the-art ASR model for each target language, using approximately 36.65 h of transcribed speech data from diverse sources enriched with data augmentation methods. We systematically investigate, using a Bayesian search, the impact of the different hyperparameters on the Wav2vec2.0 XLS-R (Cross-Lingual Speech Representations) variants of 300 M and 1 B parameters. Our findings indicate that data and detailed hyperparameter tuning significantly affect ASR accuracy, but language complexity determines the final result. The Quechua model achieved the lowest character error rate (CER) (12.14), while the Kotiria model, despite having the most extensive dataset during the fine-tuning phase, showed the highest CER (36.59). Conversely, with the smallest dataset, the Guarani model achieved a CER of 15.59, while Bribri and Wa'ikhana obtained, respectively, CERs of 34.70 and 35.23. Additionally, Sobol' sensitivity analysis highlighted the crucial roles of freeze fine-tuning updates and dropout rates. We release our best models for each language, marking the first open ASR models for Wa'ikhana and Kotiria. This work opens avenues for future research to advance ASR techniques in preserving minority Indigenous languages