Juan C. Leon Alcazar

Juan C. Leon Alcazar

I'm a Ph.D working on audiovusal recognition and continual learning.

Postdoctoral Fellow for the AI Initiative, KAUST

Posts by Collection

portfolio

publications

Active speakers in context

Published in CVPR, 2020

Current methods for active speaker detection focus on modeling audiovisual information from a single speaker. This strategy can be adequate for addressing single-speaker scenarios, but it prevents accurate detection when the task is to identify who of many candidate speakers are talking. This paper introduces the Active Speaker Context, a novel representation that models relationships between multiple speakers over long time horizons. Our new model learns pairwise and temporal relations from a structured ensemble of audiovisual observations. Our experiments show that a structured feature ensemble already benefits active speaker detection performance. We also find that the proposed Active Speaker Context improves the state-of-the-art on the AVA-ActiveSpeaker dataset achieving an mAP of 87.1%. Moreover, ablation studies verify that this result is a direct consequence of our long-term multi-speaker analysis.

Download here

talks