Julia Wilkins 👩‍💻 🔊

CV | Updates | Publications | Outreach | Life

Hello! I am currently a 5th-year Computer Science PhD Candidate at New York University planning to complete my PhD in Summer 2026. I work in the Music and Audio Research Laboratory and am advised by Juan Pablo Bello and Magdalena Fuentes. My current research interests lie in self-supervised audio representation learning, sometimes in a multimodal setting with audio-visual or audio-text data, and machine listening more broadly. During my PhD, I have been fortunate to have fruitful research internships at Adobe, Bosch, and SiriusXM/Pandora.

🚀 I will be seeking full-time Research Scientist roles in Fall 2026. Let’s chat at WASPAA, DCASE or ICASSP this year! 🚀

Prior to joining NYU, I was a Data Scientist/Engineer at Sonos in Seattle. I completed my undergraduate degree in Computer Science and Music Technology at Northwestern University in 2018, and have Prof. Bryan Pardo and the Interactive Audio Lab to thank for fueling my interest in music information retrieval research at an early stage.

Updates

[September 2025] Another one of Sivan and my works on audio representation disentanglement has been accepted to the DCASE Workshop! I will be presenting a poster on this work in Barcelona at the end of October. Paper link to come soon!
[July 2025] My paper on self-supervised music representation disentanglement was accepted to WASPAA 2025! 🎉 See you in Tahoe!
[June 2025] I am looking forward to interning at SiriusXM-Pandora this summer working on audio representation learning for large-scale music recommendation and retrieval, with mentors Matt McCallum, Jaehun Kim, and Matthew Davies!
[November 2024] I will be at ISMIR 2024 in San Francisco, presenting a Late Breaking Demo on self-supervised audio disentanglement. Come say hi!
[Summer 2024] Looking forward to interning at Bosch Research this summer, working with Ho-Hsiang Wu, Luca Bondi, and Winston Lin!
[September 2023] My paper in collaboration with Bosch Research was accepted to the DCASE 2023 Workshop!
[June 2023] My paper in collaboration with Adobe research was accepted to WASPAA 2023! Check out our exciting project website here!
[May 2023] I’m looking forward to returning to Adobe Research in San Francisco this summer!
[May 2022] I’ll be joining the audio team at Adobe Research this summer working on on multimodal machine learning with Justin Salamon and Oriol Nieto.

Publications

Latent Multi-view Learning for Robust Environmental Sound Representations
Sivan Ding, Julia Wilkins, Magdalena Fuentes, Juan Pablo Bello. Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE), 2023. [📄 Paper coming soon!]
Balancing Information Preservation and Disentanglement in Self-Supervised Music Representation Learning
Julia Wilkins, Sivan Ding, Magdalena Fuentes, Juan Pablo Bello. IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2025. [📄 Paper]
Self-Supervised Multi-View Representation Learning for Disentangled Music Audio Representations
Julia Wilkins, Sivan Ding, Magdalena Fuentes, Juan Pablo Bello. Late Breaking Demo at International Society for Music Information Retrieval (ISMIR), 2024 [📄 Paper][💻 Website]
Bridging High-Quality Audio and Video via Language for Sound Effects Retrieval from Visual Queries
Julia Wilkins, Justin Salamon, Magdalena Fuentes, Juan Pablo Bello, Oriol Nieto. IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2023.
[📄 Paper] [💻 Website]
Two vs. Four-Channel Sound Event Localization and Detection
Julia Wilkins, Magdalena Fuentes, Luca Bondi, Shabnam Ghaffarzadegan, Ali Abavisani, Juan Pablo Bello. Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE), 2023. [📄 Paper]
Urban sound & sight: Dataset and benchmark for audio-visual urban scene understanding
Magdalena Fuentes, Bea Steers, Pablo Zinemanas, Martín Rocamora, Luca Bondi, Julia Wilkins, Qianyi Shi, Yao Hou, Samarjit Das, Xavier Serra, Juan Pablo Bello IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022.
[📄 Paper] [💻 Dataset]
Exploring a Probabilistic Approach to Vehicle Sound Source Localization in Urban Scenes
Julia Wilkins, Magdalena Fuentes, et al. Sight and Sound Workshop at CVPR 2022.
[📄 Paper]
VocalSet: A Singing Voice Dataset
Julia Wilkins, Prem Seetharaman, Alison Wahl, Bryan Pardo. International Society for Music Information Retrieval (ISMIR), 2018.
[📄 Paper] [💻 Dataset]
MedleyDB 2.0: New Data and a System for Sustainable Data Collection
Rachel Bittner, Julia Wilkins, Hanna Yip, Juan Pablo Bello. Late Breaking Demo at International Society for Music Information Retrieval (ISMIR), 2016.
[📄 Paper] [💻 Dataset]

Please refer to my Google Scholar for more information.

Teaching / Outreach

I put together a tutorial with Xavier Juanola Molet on using ⚡PyTorch Lightning⚡ and 👩‍💻Weights and Biases👩‍💻 to improve your machine learning workflow!
From 2019-2021, I was a volunteer teacher with Microsoft TEALS. I led academic year-long remote introductory Python courses at rural Washington high schools while working at Sonos, and hope to do more of this in the future!
I’m passionate about animal welfare and finding homes for dogs in urban environments. In New York, I’ve worked with the NYC ACC. Previously, I volunteered for 2 years at the Seattle Animal Shelter, and before then I was at the Evanston Animal Shelter.

Academic Service

ICASSP 2024, reviewer
DCASE 2023 Workshop, reviewer
WASPAA 2023, reviewer
ICASSP 2023, reviewer
ICASSP 2022, reviewer
TISMIR 2022, reviewer

Life

Outside of research and working with animals, I enjoy rock climbing, running, cycling, exploring NYC coffee shops, and training my husky-shepherd mix, Kona.