Automated speech recognition of Indonesian-English language lessons on YouTube using transfer learning

Zara Maxwell-Smith, Ben Foley


Abstract
Experiments to fine-tune large multilingual models with limited data from a specific domain or setting has potential to improve automatic speech recognition (ASR) outcomes. This paper reports on the use of the Elpis ASR pipeline to fine-tune two pre-trained base models, Wav2Vec2-XLSR-53 and Wav2Vec2-Large-XLSR-Indonesian, with various mixes of data from 3 YouTube channels teaching Indonesian with English as the language of instruction. We discuss our results inferring new lesson audio (22-46% word error rate) in the context of speeding data collection in diverse and specialised settings. This study is an example of how ASR can be used to accelerate natural language research, expanding ethically sourced data in low-resource settings.
Anthology ID:
2023.fieldmatters-1.1
Volume:
Proceedings of the Second Workshop on NLP Applications to Field Linguistics
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Oleg Serikov, Ekaterina Voloshina, Anna Postnikova, Elena Klyachko, Ekaterina Vylomova, Tatiana Shavrina, Eric Le Ferrand, Valentin Malykh, Francis Tyers, Timofey Arkhangelskiy, Vladislav Mikhailov
Venue:
FieldMatters
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–16
Language:
URL:
https://aclanthology.org/2023.fieldmatters-1.1
DOI:
10.18653/v1/2023.fieldmatters-1.1
Bibkey:
Cite (ACL):
Zara Maxwell-Smith and Ben Foley. 2023. Automated speech recognition of Indonesian-English language lessons on YouTube using transfer learning. In Proceedings of the Second Workshop on NLP Applications to Field Linguistics, pages 1–16, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Automated speech recognition of Indonesian-English language lessons on YouTube using transfer learning (Maxwell-Smith & Foley, FieldMatters 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.fieldmatters-1.1.pdf
Video:
 https://aclanthology.org/2023.fieldmatters-1.1.mp4