Aurora Cramer (she/her) is currently a PhD Candidate studying Electrical and Computer Engineering at New York University, under the direction of Juan Pablo Bello. Her research focuses on using natural structure in audio data from hierarchical relationships, task relationships, multi-modal dynamics, and embodied navigation to learn effective audio representations for machine listening tasks without large annotated datasets.
Aurora obtained her B.S. in Electrical Engineering and Computer Sciences from U.C. Berkeley in 2015, where she completed the EECS Honors program with a focus in Music/Audio. In 2017, Aurora started her graduate studies in Electrical and Computer Engineering in the Masters program at New York University as a Samuel Morse Fellow, before transferring to the PhD program in 2018. She is currently involved in the SONYC and BirdVox projects.
Aurora has worked in the space of audio and machine learning in industry. Most recently, she was an intern at Mitsubishi Electric Research Laboratories during the Fall of 2020 working on environment source separation. Previously, she was an intern on the Applied Deep Learning Research team at NVIDIA during the summer of 2018 working on audio inpainting. She was as a research engineer on the Applied Research team at Gracenote from 2015-2017 where she developed audio classification systems for music. In 2014, she was a media engineering intern at BlueJeans Network, where she worked on refactoring, testing, and improving noise suppression systems for video conferencing platforms.
Outside of academic interests, her interests include music, wordplay, wholesomeness, whimsy, absurdity, cuteness, UNIX, and cats and dogs.