SCAN adds framewise voice comparison between reference speech and candidate audio to active speaker detection, improving mAP on Ego4D over the TalkNet and Light-ASD baselines.
Combining Residual Networks with LSTMs for Lipreading,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MM 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings
SCAN adds framewise voice comparison between reference speech and candidate audio to active speaker detection, improving mAP on Ego4D over the TalkNet and Light-ASD baselines.