Title :
Speech-driven eyebrow motion synthesis with contextual Markovian models
Author :
Yu Ding ; Radenen, Mathieu ; Artieres, Thierry ; Pelachaud, Catherine
Author_Institution :
LIP6, Univ. Pierre et Marie Curie, Paris, France
Abstract :
Nonverbal communicative behaviors during speech are important to model a virtual agent able to sustain a natural and lively conversation with humans. We investigate statistical frameworks for learning the correlation between speech prosody and eyebrow motion features. Such methods may be used to synthesize automatically accurate eyebrow movements from synchronized speech.
Keywords :
Markov processes; multi-agent systems; speech processing; speech synthesis; contextual Markovian model; eyebrow motion features; eyebrow movement; nonverbal communicative behavior; speech prosody; speech-driven eyebrow motion synthesis; statistical framework; synchronized speech; virtual agent; Animation; Computational modeling; Eyebrows; Hidden Markov models; Speech; Trajectory; Vectors; Hidden Markovian models; speech to motion synthesis; virtual agent;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on
Conference_Location :
Vancouver, BC
DOI :
10.1109/ICASSP.2013.6638360
