Data Augmentation and Hyperparameter Tuning for Low-Resource MFA
Not on the map. Why?
Abstract (arXiv)
A continued issue for those working with computational tools and endangered and under-resourced languages is the lower accuracy of results for languages with smaller amounts of data. We attempt to ameliorate this issue by using data augmentation methods to increase corpus size, comparing augmentation to hyperparameter tuning for multilingual forced alignment. Unlike text augmentation methods, audio augmentation does not lead to substantially increased performance. Hyperparameter tuning, on the other hand, results in substantial improvement without (for this amount of data) infeasible additional training time. For languages with small to medium amounts of training data, this is a workable alternative to adapting models from high-resource languages.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 8 of its 21 references that are in the map. First posted on arXiv 9 Apr 2025.
Builds on
8 of 21 references.
References · 8
- 2021An Empirical Survey of Data Augmentation for Limited Data Learning in NLPcited by 101
- 2021Data Augmentation Approaches in Natural Language Processing: A Surveycited by 82
- 2021MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognitioncited by 39
- 2021To Augment or Not to Augment? A Comparative Study on Text Augmentation Techniques for Low-Resource NLPcited by 12
- 2023Data Augmentation for Neural Machine Translation using Generative Language Modelcited by 12
- 2021Leveraging pre-trained representations to improve access to untranscribed speech from endangered languagescited by 8
- 2021An Ensemble 1D-CNN-LSTM-GRU Model with Data Augmentation for Speech Emotion Recognitioncited by 8
- 2023Hate Speech Detection in Limited Data Contexts using Synthetic Data Generationcited by 3
Built on by
Citing papers per year: 2025: 1.
1 paper.