About me

I head the Sound Design AI Group (SODA) at Adobe Research in San Francisco,  where I'm a Principal Scientist. My team works on AI for sound generation and understanding for video. We developed and ship impactful audio AI models, such as Firefly Generate Sound Effects and Generative Extend in Premiere Pro. We conduct innovative research and publish at top academic conferences.

My research focuses on the application of machine learning and signal processing to audio & video, with applications in sound generation and understanding, machine listening, audiovisual and multi-modal understanding, representation learning & self-supervision, audio for video, music information retrieval, bioacoustics, environmental sound analysis and open source software & data.

Internships at Adobe: My team and I are always looking for strong graduate students to collaborate with. If you are interested in interning at Adobe Research with our group, please send me an email introducing yourself and describe your research interests and experience.

A little about me: I went to an arts-focused high school, majoring in music (jazz guitar). Between 2004 and 2007 I studied for a Bachelors degree in Computer Science at the University of Cambridge, UK, graduating with a First Class degree including awards for outstanding dissertation and achievement in a physical subject. In 2008 I completed my Master's degree with the Music Technology Group (MTG) of Pompeu Fabra University (UPF) in Barcelona, Spain, under the supervision of Emilia Gómez. In 2013 I completed my PhD thesis in Computer Science under the supervision of Emilia Gómez and Xavier Serra. In 2011 I was also a visiting researcher at the Sound Analysis/Synthesis team at IRCAM Paris, working with Geoffroy Peeters and Axel Röbel. I completed my postdoc at NYU under the mentorship of Juan Pablo Bello. I joined Adobe in 2019, and have been leading the SODA group since 2023.