Recent advancements in multilingual models for automatic speech recognition (ASR) have been able to achieve a high accuracy for languages with extremely limited resources. This study examines ASR modeling for the Mvskoke language, an indigenous language of America. The parameter efficiency of adapter training is contrasted with training entire models, and it is demonstrated how performance varies with different amounts of data. Additionally, the models are evaluated with trigram language model decoding, and the outputs are compared across different types of speech recordings. Results show that training an adapter is both parameter efficient and gives higher accuracy for a relatively small amount of data.

This paper is a discussion of how NLP can come alongside community efforts to aid in revitalizing the Mvskoke language. Mvskoke is a language indigenous to the southeastern United States that has seen an increase in language revitalization efforts in the last few years. This paper presents an overview of available resources in Mvskoke, an exploration of relevant NLP tasks and related work in endangered language contexts, and applications to language revitalization.