{"title":"A Speech Promotion System by Using Embodied Entrainment Objects of Spoken Words and a Listener Character for Joint Attention","authors":"Masakatsu Kubota, Tomio Watanabe, Yutaka Ishii","doi":"10.1145/3349537.3352803","DOIUrl":null,"url":null,"abstract":"We have developed a speech promotion system that presents images retrieved based on spoken words on a display and shows the auto-generated nodding reaction of the search images with a listener character. The online image search function can respond to various utterances of the user. In this research, in order to speed up the time to present images, we prepare not only the online image search function but also the pre-stored image call function. Moreover, the listener character in the system moves to look at the image at the same time that it appears. This character's motion prompts the user to observe the image by joint attention guidance. Thus, the system promotes user's speech by the auto-generated nodding reaction of the listener character and images related to spoken words.","PeriodicalId":188834,"journal":{"name":"Proceedings of the 7th International Conference on Human-Agent Interaction","volume":"11 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 7th International Conference on Human-Agent Interaction","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3349537.3352803","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
We have developed a speech promotion system that presents images retrieved based on spoken words on a display and shows the auto-generated nodding reaction of the search images with a listener character. The online image search function can respond to various utterances of the user. In this research, in order to speed up the time to present images, we prepare not only the online image search function but also the pre-stored image call function. Moreover, the listener character in the system moves to look at the image at the same time that it appears. This character's motion prompts the user to observe the image by joint attention guidance. Thus, the system promotes user's speech by the auto-generated nodding reaction of the listener character and images related to spoken words.