2 papers
cs.CL2025
Synthetic Data Generation for Phrase Break Prediction with Large Language Model
Hoyeon Lee, Sejung Son, Ye-Eun Kang +1
Current approaches to phrase break prediction address crucial prosodic aspects of text-to-speech systems but heavily rely on vast human annotations from audio or text, incurring si…
cs.CL2024
A Two-Step Approach for Data-Efficient French Pronunciation Learning
Hoyeon Lee, Hyeeun Jang, Jong-Hwan Kim +1
Recent studies have addressed intricate phonological phenomena in French, relying on either extensive linguistic knowledge or a significant amount of sentence-level pronunciation d…