AI Research Scientist · Tech Lead at NAVER Cloud
I am a Senior AI Research Scientist and Tech Lead in the Voice team at NAVER Cloud. My research focuses on Speech-Language & Multimodal AI and Large Language Models, with the goal of building AI systems that understand, reason, and interact across speech, language, and context.
I work on language and speech technologies for real-world AI products, spanning pronunciation modeling, phrase break prediction, data generation, and model evaluation. Recently, I have been exploring how LLMs can extend these systems through multimodal reasoning, tool use, and scalable agentic applications.
I connect research and engineering through technical leadership, mentoring, and production deployment. Since 2026, I have also served as an AI Technical Mentor at AI·SW Maestro.
- Speech-Language & Multimodal AI — unified understanding, reasoning, and generation across speech, language, and context
- LLMs & Agentic Applications — post-training, evaluation, tool use, and scalable real-world applications
- EMNLP 2026 — Phonemizing User-Generated Text: A Benchmark, Taxonomy, and Compositional Approach
- INTERSPEECH 2026 — LLM-Based Multi-Reference Evaluation for Efficient and Robust Assessment of Phrase Break Annotations
- INTERSPEECH 2025 — Synthetic Data Generation for Phrase Break Prediction with Large Language Model
- EMNLP 2024 — A Two-Step Approach for Data-Efficient French Pronunciation Learning
For a complete publication list, please visit my Google Scholar profile.
— a multilingual G2P benchmark for user-generated text, published at EMNLP 2026
— practical NLP tutorials and reproducible implementations in Jupyter notebooks
I enjoy turning research ideas into clear, reproducible resources and dependable AI systems. If you are interested in Speech-Language & Multimodal AI, LLMs, agentic applications, or research collaboration, feel free to reach out.