Introduction

My research explores how machines can make sense of music and the sounds around us. Together with my students, I develop signal processing and machine learning methods that help computers listen, interpret, and reason about sound.

I’m particularly interested in how sound connects with vision and language, what machine learning models actually understand about the acoustic world, and how we can make them more robust, interpretable, and reliable. Our work spans music information retrieval, environmental sound understanding, multimodal analysis and synthesis, and applications in accessibility and health.