2021/06/07 by Okan Köpüklü, Köpüklü, Okan, Maja Taseska +3 · 6 citations
Computer Science · Engineering · #Music and Audio Processing #Speech Recognition and Synthesis #Speech and Audio Processing #cs.CV #cs.LG #cs.SD #eess.AS
paper · pdf · doi:10.48550/arxiv.2106.03932
Accepted to ICCV 2021
arxiv created 2021/09/07 · arxiv updated 2021/09/08
Successful active speaker detection requires a three-stage pipeline: (i) audio-visual encoding for all speakers in the clip, (ii) inter-speaker relation modeling between a reference speaker and the background speakers within each frame, and (iii) temporal modeling for the reference speaker. Each stage of this pipeline plays an important role for the final performance of the created architecture. Based on a series of controlled experiments, this work presents several practical guidelines for audio-visual active speaker detection. Correspondingly, we present a new architecture called ASDNet, which achieves a new state-of-the-art on the AVA-ActiveSpeaker dataset with a mAP of 93.5% outperforming the second best with a large margin of 4.7%. Our code and pretrained models are publicly available.