Enhancing Korean-Accented English ASR with Transliteration-Based Data Synthesis
Electronics · 26.03.2026 · 15 (7) · 1380
DOI: 10.3390/electronics15071380 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 26.03.2026. Verfasst von Hana Jang und 3 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute of Information & Communications Technology Planning & Evaluation https://ror.org/01g0hqq23.
Abstract (Originalsprache)
Despite recent advances in automatic speech recognition (ASR), performance remains limited for Korean-accented English due to the limited availability of accent-specific speech data, including pronunciation and prosodic variations. To address this limitation, we propose a synthetic data generation framework for improving Whisper-based ASR performance. Synthetic speech is generated by converting English text into Hangul-based phonetic transcriptions using an intermediate IPA representation to reflect the phonological characteristics of Korean-accented English. The ASR model is fine-tuned using Low-Rank Adaptation with a mixture of synthetic and authentic speech data. Experimental results demonstrate relative reductions of up to 16.40% in the character error rate, 14.93% in the word error rate, and 14.81% in the phoneme error rate compared to the pretrained baseline.
Förderung
- Institute of Information & Communications Technology Planning & Evaluation https://ror.org/01g0hqq23
Zitieren
APA
Jang, H., Kim, T., Choi, H., & Jung, Y. (2026). Enhancing Korean-Accented English ASR with Transliteration-Based Data Synthesis. Electronics, 15(7), 1380. https://doi.org/10.3390/electronics15071380
Vancouver
Jang H, Kim T, Choi H, Jung Y. Enhancing Korean-Accented English ASR with Transliteration-Based Data Synthesis. Electronics. 2026;15(7):1380. doi:10.3390/electronics15071380
BibTeX
@article{Jang2026,
author = {Jang, Hana and Kim, Taehwa and Choi, Hyungwoo and Jung, Youngbeom},
title = {Enhancing Korean-Accented English ASR with Transliteration-Based Data Synthesis},
journal = {Electronics},
year = {2026},
volume = {15},
number = {7},
pages = {1380},
doi = {10.3390/electronics15071380}
}
EUVIMED