[2603.26248] Automatic Speech Recognition for Documenting Endangered Languages: Case Study of Ikema Miyakoan

Computer Science > Computation and Language arXiv:2603.26248 (cs) [Submitted on 27 Mar 2026] Title:Automatic Speech Recognition for Documenting Endangered Languages: Case Study of Ikema Miyakoan Authors:Chihiro Taguchi, Yukinori Takubo, David Chiang View a PDF of the paper titled Automatic Speech Recognition for Documenting Endangered Languages: Case Study of Ikema Miyakoan, by Chihiro Taguchi and 2 other authors View PDF Abstract:Language endangerment poses a major challenge to linguistic diversity worldwide, and technological advances have opened new avenues for documentation and revitalization. Among these, automatic speech recognition (ASR) has shown increasing potential to assist in the transcription of endangered language data. This study focuses on Ikema, a severely endangered Ryukyuan language spoken in Okinawa, Japan, with approximately 1,300 remaining speakers, most of whom are over 60 years old. We present an ongoing effort to develop an ASR system for Ikema based on field recordings. Specifically, we (1) construct a {\totaldatasethours}-hour speech corpus from field recordings, (2) train an ASR model that achieves a character error rate as low as 15\%, and (3) evaluate the impact of ASR assistance on the efficiency of speech transcription. Our results demonstrate that ASR integration can substantially reduce transcription time and cognitive load, offering a practical pathway toward scalable, technology-supported documentation of endangered languages. Comments: ...