Rigid Head Motion in Expressive Speech Animation: Analysis and Synthesis

Busso, Carlos; Deng, Zhigang; Grimm, Michael; Neumann, Ulrich; Narayanan, Shrikanth

doi:10.1109/tasl.2006.885910

Cited by 157 publications

(96 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Table 3 presents the statistics of motion angle at frame level, and Amp and Avg at prosodic word level. The statistics suggest head pitch has higher motion activity than head yaw and roll at both frame and prosodic word level, confirming the results reported in [5], and also indicates head nods are significant motion patterns found in our corpus.…”

Section: Head Motion Features Extractionsupporting

confidence: 91%

“…Since the PAD model is originally designed for human emotion evaluation, it is the most popular and recommend way to obtain PAD values through human ratings [4,5,31]. Previous engineering approaches have gain convincible PAD values from human annotation [3] and predefined rules [26,38].…”

Section: Discussionmentioning

confidence: 99%

“…Previous studies measure head motions in Euler angles of rotation around x-(pitch), y-(yaw), and z-axis (roll) respectively [5,18,34]. The three rotation angles are also defined in the MPEG-4 facial animation parameters (FAP) [32].…”

Section: Head Motion Features Extractionmentioning

confidence: 99%

“…To analyze head motion, previous speech-driven approaches investigate the acoustic correlates with motion features at the frame level [5,34]. However, longer range dependencies rather than frame-wise correlation, were found between acoustic and motion features in other study based on different dataset [20].…”

Section: Head Motion Features Extractionmentioning

confidence: 99%

“…Audio-visual database have also been collected to support data-driven approach that selects the video segments best-matched to the pitch contour of speech and stitch them together to create synthetic head motions [9]. Head motions are further analyzed and synthesized to express emotions of several categories [5].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Head and facial gestures synthesis using PAD model for an expressive talking avatar

Jia

Zhang

et al. 2013

Multimed Tools Appl

View full text Add to dashboard Cite

This paper proposes to synthesize expressive head and facial gestures on talking avatar using the three dimensional pleasure-displeasure, arousal-nonarousal and dominancesubmissiveness (PAD) descriptors of semantic expressivity. The PAD model is adopted to bridge the gap between text semantics and visual motion features with three dimensions of pleasure-displeasure, arousal-nonarousal, and dominance-submissiveness. Based on the correlation analysis between PAD annotations and motion patterns derived from the head and facial motion database, we propose to build an explicit mapping from PAD descriptors to facial animation parameters with linear regression and neural networks for head motion and facial expression respectively. A PAD-driven talking avatar in text-to-visual-speech system is implemented by generating expressive head motions at the prosodic word level based on the (P, A) descriptors of lexical appraisal, and facial expressions at the sentence level according to the PAD descriptors of emotional information. A series of PAD reverse evaluation and comparative perceptual experiments shows that the head and facial gestures synthesized based on PAD model can significantly enhance the visual expressivity of talking avatar.

show abstract

Section: Head Motion Features Extractionsupporting

confidence: 91%