Saved in:
Bibliographic Details
Main Authors: Taguchi, Chihiro, Takubo, Yukinori, Chiang, David
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.26248
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917419737415680
author Taguchi, Chihiro
Takubo, Yukinori
Chiang, David
author_facet Taguchi, Chihiro
Takubo, Yukinori
Chiang, David
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_26248
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Automatic Speech Recognition for Documenting Endangered Languages: Case Study of Ikema Miyakoan
Taguchi, Chihiro
Takubo, Yukinori
Chiang, David
Computation and Language
Artificial Intelligence
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.
title Automatic Speech Recognition for Documenting Endangered Languages: Case Study of Ikema Miyakoan
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2603.26248