Anna Huang is the Robert N. Noyce Career Development Professor at MIT, with a shared appointment between the Music & Theater Arts Section and Electrical Engineering and Computer Science (EECS). Previously, she spent eight years with the Magenta team at Google Brain and Google DeepMind, spearheading efforts in generative modeling, reinforcement learning, and human-computer interaction to support human-AI partnerships in music-making.
She is the creator of the ML model Coconet that powered Google’s first AI Doodle, the Bach Doodle. In two days, Coconet harmonized 55 million melodies from users around the world. In 2018, she created Music Transformer, a breakthrough in generating music with long-term structure, and the first successful adaptation of the transformer architecture to music. Her ICLR paper is one of the most cited papers in music generation.
She held a Canada CIFAR AI Chair at Mila – Québec AI Institute, and an adjunct professorship at Université de Montréal. She did her PhD at Harvard University and was a recipient of the NSF Graduate Research Fellowship. She has a master’s from the MIT Media Lab, and a dual bachelor’s from University of Southern California in music composition and CS.
As a composer, she wrote for soloists, mixed chamber groups and orchestra, as well as tape and live electronics. Her electronic work has been performed on the 40-channel HYDRA loudspeaker orchestra. Her compositions have won awards including first place in the San Francisco Choral Artists’ a cappella composition contest. She is part of the founding team of the AI Song Contest, served as one of three inaugural judges in 2020, and a core organizer for 2021 and 2022. She has served as guest editor for ISMIR’s flagship journal, proposing and co-editing TISMIR's special issue on AI and Musical Creativity.
She takes an interaction-driven approach to designing Generative AI, to enable new ways of interacting with music (and AI) that can extend how we understand, learn, and create music. She aims to partner with musicians, to design for the specificity of their creative practice and tradition, which inevitably invites new ways of thinking about generative modeling and Human-AI collaboration.
She proposes to use neural networks (NNs) as a lens onto music, and a mirror onto our own understanding of music. I’m interested in music theories and music cognition of NNs and for NNs, to understand, regularize and calibrate their musical behaviors. She aims to work towards interpretability and explainability that is useful for musicians interacting with the AI system. She envisions working with musicians to design interactive systems and visualizations that empower them to understand, debug, steer, and align the generative AI’s behavior.
She is also interested in rethinking generative AI through the lens of social reinforcement learning (RL) and multi-agent RL, to elicit creativity not through imitation but through interaction. This framework invites us to consider how game design and reward modeling can influence how agents and users interact. She envisions a jam space, where musicians and agents can jam together, and researchers can swap in their own generative agents and reward models, similar to OpenAI’s Gym. The evaluation is not only on the resulting music, but also on the interactions, how well agents support other players. She is also interested in efficient machine learning, to build instruments and agents that can run in real-time, to enable Human-AI collective improvisation.