Hao-Wen Dong

My research aims to empower music and audio creation with machine learning. My long-term goal is to lower the barrier of entry for music composition and democratize audio content creation. I am broadly interested in music generation, audio synthesis, generative AI, multimodal learning, and music information retrieval. I study a wide range of topics centered around Generative AI for Music and Audio, including multitrack music generation, automatic instrumentation, automatic arrangement, automatic harmonization, music performance synthesis, text-queried sound separation, text-to-audio synthesis and symbolic music processing software.