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.

Usage-based analyses of teacher corpora and code-switching (Boztepe, 2003) are an important next stage in understanding language acquisition. Multilingual corpora are difficult to compile and a classroom setting adds pedagogy to the mix of factors which make this data so rich and problematic to classify. Using quantitative methods to understand language learning and teaching is difficult work as the ‘transcription bottleneck’ constrains the size of datasets. We found that using an automatic speech recognition (ASR) toolkit with a small set of training data is likely to speed data collection in this context (Maxwelll-Smith et al., 2020).

This paper focuses on the technical improvement of Elpis, a language technology which assists people in the process of transcription, particularly for low-resource language documentation situations. To provide better support for the diversity of file formats encountered by people working to document the world’s languages, a Data Transformer interface has been developed to abstract the complexities of designing individual data import scripts. This work took place as part of a larger project of code quality improvement and the publication of template code that can be used for development of other language technologies.

Multilingual corpora are difficult to compile and a classroom setting adds pedagogy to the mix of factors which make this data so rich and problematic to classify. In this paper, we set out methodological considerations of using automated speech recognition to build a corpus of teacher speech in an Indonesian language classroom. Our preliminary results (64% word error rate) suggest these tools have the potential to speed data collection in this context. We provide practical examples of our data structure, details of our piloted computer-assisted processes, and fine-grained error analysis. Our study is informed and directed by genuine research questions and discussion in both the education and computational linguistics fields. We highlight some of the benefits and risks of using these emerging technologies to analyze the complex work of language teachers and in education more generally.