Facial Expression Generation from Speaker's Emotional States in Daily Conversation
スポンサーリンク
概要
- 論文の詳細を見る
A framework for generating facial expressions from emotional states in daily conversation is described. It provides a mapping between emotional states and facial expressions, where the former is represented by vectors with psychologically-defined abstract dimensions, and the latter is coded by the Facial Action Coding System. In order to obtain the mapping, parallel data with rated emotional states and facial expressions were collected for utterances of a female speaker, and a neural network was trained with the data. The effectiveness of proposed method is verified by a subjective evaluation test. As the result, the Mean Opinion Score with respect to the suitability of generated facial expression was 3.86 for the speaker, which was close to that of hand-made facial expressions.
- （社）電子情報通信学会の論文
- 2008-06-01
著者
-
Mori Hiroki
Faculty of Engineering, Utsunomiya University
-
Mori Hiroki
Faculty Of Engineering Utsunomiya University
-
OHSHIMA Koh
Faculty of Engineering, Utsunomiya University
-
Ohshima Koh
Faculty Of Engineering Utsunomiya University
関連論文
- Generative model of F_0 change field for Mandarin trisyllabic words
- Statistical examination of invariance of relative F_0 change field for Chinese disyllabic words
- Evaluation of fundamental frequency (F_0) characteristics of speech in dysarthrias : A comparative study
- Prosodic variations in disyllabic meaningful words focused with different stress patterns in Mandarin Chinese
- Some considerations for designing spoken dialogue database from the viewpoint of paralinguistic information
- Effects of speaking rate on mora timing organization in producing Japanese contrastive geminate/single consonants and long/short vowels by native and Chinese speakers
- F_0 Dynamics in Singing : Evidence from the Data of a Baritone Singer(Speech Dynamics by Ear, Eye, Mouth and Machine)
- Facial Expression Generation from Speaker's Emotional States in Daily Conversation