Published paper: 'Visual Sound Source Localization: Assessing Performance with Both Positive and Negative Audio'; Student Member of the ISMIR Board; Reviewer for multiple academic journals and conferences, including WASPAA, ISMIR, TASLP, TISMIR, and ICASSP.
Research Experience
Presented research at various academic conferences and workshops, such as the Sight and Sound Workshop.
Education
PhD Candidate at New York University, supervised by Magdalena Fuentes.
Background
PhD Candidate at New York University and a member of the Music and Audio Research (MARL) lab, supervised by Magdalena Fuentes. Interested in multimodal models (audio-vision, audio-text), explainability techniques, and music information retrieval. Likes to think about Deep Learning from a data-centric perspective, investigating how biased datasets can affect model behavior and how we can explain a model output.
Miscellany
Organized events: 2024 LAMIR hackathon and logistics; Student organizer of LatAm Bish BASH since 2023; Teaching Assistant for Deep Learning for Media (MPATE-GE-2039) in Spring 2025.