A methodological study of situation understanding utilizing environments for multimodal observation of infant behavior

  • Authors:
  • Shogo Ishikawa;Shinya Kiriyama;Hiroaki Horiuchi;Shigeyoshi Kitazawa;Yoichi Takebayashi

  • Affiliations:
  • Shizuoka University, Shizuoka Japan;Shizuoka University, Shizuoka Japan;Shizuoka University, Shizuoka Japan;Shizuoka University, Shizuoka Japan;Shizuoka University, Shizuoka Japan

  • Venue:
  • Proceedings of the 1st ACM international workshop on Human-centered multimedia
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

We have developed a framework to understand situations and intentions of speakers focusing on the utterances of demonstratives. We aim at constructing a 'Multimodal Infant Behavior Corpus', which makes a valuable contribution to the elucidation of human commonsense knowledge and its acquisition mechanism. For this purpose, we have constructed environments for multimodal observation of infant behavior, in particular, environments for infant behavior recording; we have set up multiple cameras and microphones in the Cedar yurt. We have also developed a wearable speech recording device of high quality to capture infant utterances clearly. Moreover, we have developed a comment-collecting system which allows everyone to make comments easily from the multi-viewpoints. Those construction and developments make it possible to realize a framework for multimodal observation of infant behavior. Utilizing the multimodal environments, we propose a situation description model based on observation of demonstratives uttered by infants, since demonstratives appear frequently in their conversations and become a precious clue to understand situations. The proposed model, which represents the mental distances of speakers and listeners to objects on a general and simple model, enables us to predict speakers' next behavior. The consideration results enable us to conclude that the constructed environments lead to development and realization of human interaction models applicable to spoken dialog systems for elder people supporting.