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

TL;DR

This paper develops an automatic speech recognition system for the endangered Ikema language, demonstrating its effectiveness in reducing transcription time and aiding language documentation efforts.

Contribution

It presents a new ASR system trained on field recordings for Ikema, an endangered language, with promising accuracy and practical transcription benefits.

Findings

ASR system achieved a 15% character error rate.

ASR assistance reduced transcription time significantly.

The approach supports scalable documentation of endangered languages.

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 6.33-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.