Logo image
Atayal Speech Recognition Based on Transfer Learning
Conference proceeding

Atayal Speech Recognition Based on Transfer Learning

Po Cheng Chan, Manh-Quan Bui, Ching-Ting Hsin, Di Tam Luu, Chi-Tao Chen and Jia Ching Wang
2025 RIVF International Conference on Computing and Communication Technologies (RIVF), pp.1-6
18/12/2025

Abstract

Automatic speech recognition Computational modeling Cross lingual Documentation Error analysis Multilingual Speech Recognition Speech to text Speech Transcription Transfer learning Translation Tuning
This work investigates automatic speech recognition (ASR) and cross-lingual transcription for Atayal, an endangered Austronesian language spoken in Taiwan, by leveraging the Whisper-medium pre-trained model. We finetuned two task-specific systems: one for direct Atayal speech-to-text transcription and another for Atayal speech-toChinese translation. Both models were trained on a bilingual Atayal-Mandarin corpus and demonstrated strong performance, achieving character error rates (CER) of 3.617 % for Atayal transcription and 5.585 % for Mandarin output. The results show the effectiveness of fine-tuning large-scale ASR models for low-resource languages and demonstrate their potential to aid the documentation and preservation of endangered languages.

Metrics

1 Record Views

Details

Logo image