GeezerVison

GeezerVison is showing lyeoni.github.io — Hoyeon Lee

I am a Senior AI Research Scientist and Tech Lead in the Voice team at NAVER Cloud. I build speech and language technologies for real-world AI products, with research interests spanning LLMs and multimodal AI. I aim to contribute to leading conferences in AI/ML, NLP, and speech/audio research.

My work focuses on Multimodal AI and LLM Applications for speech and language systems, spanning robust understanding, evaluation, and real-world deployment. I connect research and engineering through technical leadership at NAVER and have mentored several AI projects at AI·SW Maestro since April 2026.

My current research interests broadly fall into two areas:

Multimodal AI: How can AI understand and interact across speech, language, and context?
LLM Applications: How can LLMs improve data generation, evaluation, tool use, and real-world AI systems?

If you are interested in collaboration or would like to get in touch, please feel free to contact me.

news

Nov 2026	Two papers submitted by teams I mentored through AI·SW Maestro were accepted to the 2026 Autumn Annual Conference of IEIE, and I served as a corresponding author on both.
Sep 2026	Our paper “Phonemizing User-Generated Text: A Benchmark, Taxonomy, and Compositional Approach,” for which I served as a corresponding author, was accepted to EMNLP 2026.
Sep 2026	Excited to share that our work “LLM-Based Multi-Reference Evaluation for Efficient and Robust Assessment of Phrase Break Annotations” will appear at INTERSPEECH 2026. Looking forward to presenting it in Sydney, Australia 🇦🇺!
Apr 2026	I joined AI·SW Maestro as a Technical Mentor. Starting this year, I mentor two teams 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 🇳🇱.