AI + Music: Empowering, Not Overpowering

FROM THE FESTIVAL ARCHIVE

“AI + Music: Empowering, Not Overpowering” examined the balance between human expression and artificial intelligence in music creation, with perspectives from Georgia Tech, NYU, Meta, Fish Audio and CMU.

Speakers and biographies from the 2025 programme:

Gil Weinberg — Professor & Founding Director, Georgia Tech Center for Music Technology
A pioneer in robotic musicianship, Weinberg’s work bridges AI, robotics, and human expression through projects that redefine creativity and collaboration.

Ziyu Wang — Postdoctoral Researcher, Courant Institute of Mathematical Sciences, NYU
Working with Prof. Yann LeCun, Wang develops music world models that merge machine learning and musical intelligence, combining academic depth with artistic practice.

Xiaosha (Evelyne) Li — Researcher / Composer / Artist, Music Informatics Group @ Georgia Tech
Li’s research on audio representation and AI interpretability bridges machine perception and musical control. Her compositions have surpassed 700,000 streams across platforms.

Helena Zhang — Co-founder & CEO, Fish Audio
Leading innovation in expressive speech generation, Zhang’s work expands the emotional and creative frontier of text-to-speech technology through Fish Audio and OpenAudio.

Rafael Valle — Research Scientist, Meta Superintelligence Lab
A generative audio expert formerly at NVIDIA, Valle’s work in multimodal understanding and AI improvisation pushes boundaries in machine creativity.

Xinyu Yang — Ph.D. Student, InfiniAI Lab & Catalyst Group, CMU
Researcher in scalable foundation model systems, Amazon AI Fellow, and founder of several global AI academic communities advancing responsible AI.