I love sound. This obsession combined with a musical and technical background led me to the path of audio research. My passion for music developed at an early age and I played guitar in various bands throughout high school and college. I also started my journey as an audiophile at that time, obsessing over high-fidelity audio capture and reproduction. I discovered digital signal processing (DSP) soon after and I was hooked. The ability to sculpt sound with math was my calling. Before heading to graduate school, I spent a year exploring audio recording and production to better understand the process and its limitations. My aspiration at the time was to revolutionize recording studios with advanced signal processing.
This led me to the Center for Computer Research in Music and Acoustics (CCRMA) at Stanford University, where I received my M.A. and Ph.D. I also received my M.S. from the department of Electrical Engineering. At Stanford, I took a deep dive into machine learning and saw the potential for it to be transformative for audio. It was the early days of deep learning, which is now becoming synonymous with modern AI. With the potential of this field, my goal started expanding to democratizing audio content creation for everyone (the universal recording studio?). What if people could very easily translate their creative ideas and stories into high quality audio content without knowing anything about audio recording, editing, or production?
As the creativity company, I was naturally drawn to Adobe and joined Adobe Research in 2010. Audio research here was in its infancy at the time. Over the next several years, I worked on various areas of audio from speech enhancement to music information retrieval with an eye towards the bigger goal. I published extensively, collaborated with academia, collaborated with product teams, was an entrepreneur in residence, and had the opportunity to work with numerous fantastic research interns. With the growing importance of audio at Adobe, I created the Audio Research Group in 2018, which we expanded to the Audio AI Lab in 2023. I have had the privilege of working with a truly world-class research team.
So, what’s coming? I think that we are now in a golden age of audio research. With the power of modern AI, I believe that we can make major strides in audio technology that were simply unimaginable just a few years ago. I think that these technical advances combined with uniquely human creativity will allow people to create audio content at a pace and quality never seen before. This ranges from music and spoken-word content to audio for video, animation, and AR/VR. I think new breeds of audio content will emerge as well. What will be the role of audio in design? How can AI supercharge people's creative aspirations? What would audio content look like if we re-imagined everything we knew about audio production for a modern world? My lab and I aim to be at the forefront of this new paradigm, inventing technical solutions to answer these questions and more.