Prem Seetharaman
Senior Research Scientist, Adobe Research
About
I am a Senior Research Scientist at Adobe Research, working in the Audio AI Lab. I received my PhD in 2019 at Northwestern University, advised by Bryan Pardo. Afterwards, I spent some time at Descript where I worked on audio enhancement and generation. My recent work focuses on generative models for all types of audio, such as every-day sounds, music, and speech. I work at the intersection of computer audition, generative modeling, and interaction, with the goal of lowering the barrier to entry for content creation.
Contact & Internships
I’m always looking for bright and motivated students to intern with me at Adobe Research! If you think you’d be a good fit, please email me with your CV and research interests at pseeth [at] adobe.com.
News
Dec 2023 I joined Adobe Research as a Senior Research Scientist, working in the Audio AI Lab.
Jul 2023 Descript launches Regenerate (led by Rithesh Kumar), powered by the Descript Audio Codec!
Jun 2023 Released VampNet, (ISMIR 2023) a really fun (and fast) unconditional music generation model with my intern Hugo!
Jun 2023 I had a kid!
May 2023 Released the Descript Audio Codec (NeurIPS 2023), a powerful neural audio codec that can compress audio 90x with minimal quality loss.
Jan 2022 First intern batch at Descript results in Wav2CLIP (ICASSP) and CARGAN (ICLR)!
Jul 2021 Shipped Studio Sound at Descript.
Feb 2021 Shipped Room Tone at Descript.
Jul 2020 Started as a Research Scientist at Descript.
May 2020 I got married!
Sep 2019 Started as a teaching post-doc at Northwestern, teaching ML.
Sep 2019 I defended my PhD! More here!
Posts
Sep 2019 Bootstrapping the learning process for computer audition
Feb 2019 Bootstrapping speech separation from unsupervised spatial separation
Jan 2019 VoiceAssist - guiding users to high-quality voice recordings
Oct 2017 Adaptive multi-cue audio source separation
Dec 2016 Cover Song ID with 2D Fourier Transform sequences
Sep 2016 Audealize: Crowdsourced Audio Production Tools
Aug 2016 Source separation and layering structure
Nov 2014 SocialReverb
Jan 2013 ClapIR