SubmissionNumber#=%=#18 FinalPaperTitle#=%=#Addressing Domain Mismatch in ASR for Akuzipik Language Documentation ShortPaperTitle#=%=# NumberOfPages#=%=#11 CopyrightSigned#=%=#Summer Chambers JobTitle#==# Organization#==# Abstract#==#The use of ASR models in endangered language documentation has grown in popularity given the bottleneck of manual speech transcription. Meta's Massively Multilingual Speech (MMS) model is particularly popular for its extensibility to low-resource languages. However, it is mostly trained on read speech data from the Bible, meaning it may not perform well on other domains. We evaluated this model on data collected as part of a larger language documentation and revitalization project focused on Akuzipik, a polysynthetic Alaska Native language. We also finetuned and evaluated the model on a small (<1h) collection of speech. The original model performed well on a dataset that roughly matched the Bible training data in domain and writing style but struggled on a separate collection of spontaneous speech. Performance on spontaneous speech improved after finetuning on a sample of our full dataset, and error rates reduced less dramatically after finetuning only on read speech. Both finetuning scenarios show promise for future model improvement, especially considering the relative ease of collecting read speech data. This experiment confirms the challenge of transcribing spontaneous speech with the MMS ASR model but provides hope for improving model performance for language documentation purposes, even with scarce data. Author{1}{Firstname}#=%=#Summer Author{1}{Lastname}#=%=#Chambers Author{1}{Username}#=%=#schamb3 Author{1}{Orcid}#=%=# Author{1}{Email}#=%=#schamb3@gmu.edu Author{1}{Affiliation}#=%=#George Mason University Author{2}{Firstname}#=%=#Sylvia L.R. Author{2}{Lastname}#=%=#Woodrose Schwartz Author{2}{Orcid}#=%=# Author{2}{Email}#=%=#sschrei2@gmu.edu Author{2}{Affiliation}#=%=#George Mason University Author{3}{Firstname}#=%=#Matthew C. Author{3}{Lastname}#=%=#Kelley Author{3}{Username}#=%=#mckelley Author{3}{Orcid}#=%=#https://orcid.org/0000-0002-7218-5599 Author{3}{Email}#=%=#mkelle21@gmu.edu Author{3}{Affiliation}#=%=#George Mason University Author{4}{Firstname}#=%=#Lane Author{4}{Lastname}#=%=#Woodrose Schwartz Author{4}{Orcid}#=%=# Author{4}{Email}#=%=#lane.schwartz@alaska.edu Author{4}{Affiliation}#=%=#University of Alaska Fairbanks ========== èéáğö