Hoyeon Lee

I am a Senior Research Scientist and Tech Lead in the Voice team at NAVER Cloud.

My research focuses on Natural Language Processing (NLP) and speech-oriented language processing for Text-to-Speech (TTS), with an emphasis on large language models (LLMs). Recently, I have been working on multilingual and cross-lingual representation learning, as well as LLM-driven methods for data generation and evaluation in speech and TTS pipelines, with a focus on scalable and robust modeling for real-world deployment.

I have developed multilingual large-scale language models covering a wide range of languages, including Korean, French, and other cross-lingual settings, and deployed them in AI products actively used across NAVER’s services. Furthermore, my work has been presented at top-tier conferences, including EMNLP, INTERSPEECH, and other leading venues.

news

Apr 2026	I joined AI·SW Maestro as a Technical Mentor. Starting this year, I mentor trainees in building production-grade AI systems across language modeling, speech AI, and multimodal intelligence.
Aug 2025	Our paper “Synthetic Data Generation for Phrase Break Prediction with Large Language Model” was accepted to INTERSPEECH 2025 in Rotterdam 🇳🇱.
Nov 2024	We presented our work “A Two-Step Approach for Data-Efficient French Pronunciation Learning” at EMNLP 2024 in Miami 🇺🇸.
Aug 2023	I give a talk on the accepted paper at INTERSPEECH2023 with slides released here!
Jun 2023	I give a talk on the accepted paper “Lightweight Grapheme-to-Phoneme Conversion Based on Knowledge Distilled BERT” at Summer Annual Conference of IEIE to be held at Jeju.