Who’s speaking? Audio-supervised classification of active speakers in video

© 2015 ACM. Active speakers have traditionally been identified in video by detecting their moving lips. This paper demonstrates the same using spatio-temporal features that aim to capture other cues: movement of the head, upper body and hands of active speakers. Speaker directional information, obtained using sound source localization from a microphone array is used to supervise the training of these video features.Chakravarty P., Mirzaei S., Tuytelaars T., Van hamme H., ''Who’s speaking? Audio-supervised classification of active speakers in video'', Proceedings 17th ACM international conference on multimodal interaction - ICMI 2015, pp. 87-90, November 9-13, 2015, Seattle, Washington, USA.status: publishe