Premium
Natural head motion synthesis driven by acoustic prosodic features
Author(s) -
Busso Carlos,
Deng Zhigang,
Neumann Ulrich,
Narayanan Shrikanth
Publication year - 2005
Publication title -
computer animation and virtual worlds
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.225
H-Index - 49
eISSN - 1546-427X
pISSN - 1546-4261
DOI - 10.1002/cav.80
Subject(s) - computer science , hidden markov model , animation , speech recognition , motion (physics) , motion capture , head (geology) , artificial intelligence , interpolation (computer graphics) , speech synthesis , computer vision , representation (politics) , computer animation , pattern recognition (psychology) , computer graphics (images) , geomorphology , politics , political science , law , geology
Natural head motion is important to realistic facial animation and engaging human–computer interactions. In this paper, we present a novel data‐driven approach to synthesize appropriate head motion by sampling from trained hidden markov models (HMMs). First, while an actress recited a corpus specifically designed to elicit various emotions, her 3D head motion was captured and further processed to construct a head motion database that included synchronized speech information. Then, an HMM for each discrete head motion representation (derived directly from data using vector quantization) was created by using acoustic prosodic features derived from speech. Finally, first‐order Markov models and interpolation techniques were used to smooth the synthesized sequence. Our comparison experiments and novel synthesis results show that synthesized head motions follow the temporal dynamic behavior of real human subjects. Copyright © 2005 John Wiley & Sons, Ltd.