3 papers
cs.MM2025
Ensembling Synchronisation-based and Face-Voice Association Paradigms for Robust Active Speaker Detection in Egocentric Recordings
Jason Clarke, Yoshihiko Gotoh, Stefan Goetze
Audiovisual active speaker detection (ASD) in egocentric recordings is challenged by frequent occlusions, motion blur, and audio interference, which undermine the discernability of…
cs.MM2025
Face-Voice Association for Audiovisual Active Speaker Detection in Egocentric Recordings
Jason Clarke, Yoshihiko Gotoh, Stefan Goetze
Audiovisual active speaker detection (ASD) is conventionally performed by modelling the temporal synchronisation of acoustic and visual speech cues. In egocentric recordings, howev…
cs.MM2025
Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings
Jason Clarke, Yoshihiko Gotoh, Stefan Goetze
Audiovisual active speaker detection (ASD) addresses the task of determining the speech activity of a candidate speaker given acoustic and visual data. Typically, systems model the…