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

Dimensions overall score 5.0

GitHub Code Pulse

No public code linked for this paper yet.

• An Automatic Speech Recognition (ASR) system was developed for the Ikema Miyakoan language.method 90%
• A speech corpus of {totaldatasethours} hours was constructed from field recordings for the Ikema Miyakoan language.method 90%
• The developed ASR model for Ikema Miyakoan achieved a character error rate as low as 15%.result 90%
• ASR integration substantially reduces transcription time.result 90%
• ASR integration substantially reduces cognitive load during speech transcription.result 90%
• The Ikema Miyakoan language has approximately 1,300 remaining speakers, most of whom are over 60 years old.technical 90%
• An Automatic Speech Recognition (ASR) system was developed for the Ikema Miyakoan language.method 95%
• A speech corpus of {totaldatasethours} hours was constructed from field recordings for the Ikema Miyakoan language.method 95%
• The developed ASR model for Ikema Miyakoan achieved a character error rate as low as 15%.result 95%
• ASR integration can substantially reduce transcription time.result 95%
• ASR integration can reduce the cognitive load of speech transcription.result 95%
• The Ikema Miyakoan language has approximately 1,300 remaining speakers, most of whom are over 60 years old.technical 95%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card