Summary
Minz Won is a Senior Research Scientist based in Boston with a decade of experience building music, audio, and speech intelligence systems that bridge academic rigor and product impact. Currently at Suno after leading music representation and retrieval research at TikTok, Minz specializes in multimodal and open-vocabulary music understanding—work that has spanned collaborations with Adobe, Pandora, and major Korean platforms. He holds a PhD in Information and Communication Technologies and a background in sound and music computing, bringing deep expertise in transformer-based audio models and text-to-music retrieval. Known for turning music semantics research into scalable recommendation and voice-assistant features, Minz also has hands-on experience in personalized advertising and production-grade sound classification systems. An uncommon thread across his career is consistent industry-academia collaboration, enabling rapid translation of novel research into real-world audio products.
10 years of coding experience
4 years of employment as a software developer
Master’s Degree Digital Contents and Information Studies, Master’s Degree Digital Contents and Information Studies at Seoul National University
Bachelor’s Degree Electronic Engineering, Bachelor’s Degree Electronic Engineering at Sogang University
Doctor of Philosophy - PhD Information and Communication Technologies, Doctor of Philosophy - PhD Information and Communication Technologies at Universitat Pompeu Fabra
Korean, English, Japanese, Spanish