Amandine Brunetto

Papers

Total Citations

H-Index

About

Amandine Brunetto is a pioneering researcher at the intersection of audio perception and computer vision, whose work is redefining how machines interpret the world through sound. Her key research areas span multimodal learning, sensor fusion, and auditory scene understanding, with a focus on leveraging audio as a complementary or alternative modality to traditional visual sensors. Brunetto’s most notable contribution is the creation of the Audio-Visual BatVision Dataset (2023), a groundbreaking resource that provides synchronized audio and visual data for research on sight and sound. This dataset addresses a critical gap in the field, where visual sensors like cameras, LiDAR, and radar may fail in low-light or adverse conditions, while sound remains a reliable cue. By enabling researchers to explore how machines can “see” with sound, her work has already garnered 3 citations and is poised to influence autonomous driving, robotics, and assistive technologies. Brunetto’s innovative approach highlights the untapped potential of audio in perception systems, making her a rising voice in multimodal AI research.