As a step toward the design of a robot that can take part to it conversation we propose a robotic system that, taking advantage of multiple perceptual capabilities, actively follows a conversation among several human subjects. The essential idea of our proposal is that the robot system can dynamically change the focus of its attention according to visual or audio stimuli to track the actual speaker throughout the conversation and infer her identity.
Multimodal speaker recognition in a conversation scenario / Marchegiani, MARIA LETIZIA; PIRRI ARDIZZONE, Maria Fiora; Pizzoli, Matia. - STAMPA. - 5815:(2009), pp. 11-20. (Intervento presentato al convegno 7th International Conference on Computer Vision Systems tenutosi a Liege, BELGIUM nel OCT 13-15, 2009) [10.1007/978-3-642-04667-4_2].
Multimodal speaker recognition in a conversation scenario
MARCHEGIANI, MARIA LETIZIA;PIRRI ARDIZZONE, Maria Fiora;PIZZOLI, MATIA
2009
Abstract
As a step toward the design of a robot that can take part to it conversation we propose a robotic system that, taking advantage of multiple perceptual capabilities, actively follows a conversation among several human subjects. The essential idea of our proposal is that the robot system can dynamically change the focus of its attention according to visual or audio stimuli to track the actual speaker throughout the conversation and infer her identity.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.