{"id":10,"date":"2020-12-30T03:58:41","date_gmt":"2020-12-29T18:58:41","guid":{"rendered":"http:\/\/iui.ci.seikei.ac.jp\/en\/?page_id=10"},"modified":"2020-12-30T17:19:17","modified_gmt":"2020-12-30T08:19:17","slug":"research","status":"publish","type":"page","link":"https:\/\/iui.ci.seikei.ac.jp\/en\/research\/","title":{"rendered":"Research"},"content":{"rendered":"<h3>Social signal processing<\/h3>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"size-medium wp-image-28 alignright\" style=\"font-size: 1rem;\" src=\"https:\/\/iui.ci.seikei.ac.jp\/en\/wp-content\/uploads\/sites\/3\/2020\/12\/groupDiscussion2-300x156.jpg\" alt=\"\" width=\"300\" height=\"156\" srcset=\"https:\/\/iui.ci.seikei.ac.jp\/en\/wp-content\/uploads\/sites\/3\/2020\/12\/groupDiscussion2-300x156.jpg 300w, https:\/\/iui.ci.seikei.ac.jp\/en\/wp-content\/uploads\/sites\/3\/2020\/12\/groupDiscussion2-768x399.jpg 768w, https:\/\/iui.ci.seikei.ac.jp\/en\/wp-content\/uploads\/sites\/3\/2020\/12\/groupDiscussion2.jpg 787w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/p>\n<p><span style=\"font-size: 1rem;\"><img loading=\"lazy\" decoding=\"async\" class=\"size-full wp-image-35 alignright\" src=\"https:\/\/iui.ci.seikei.ac.jp\/en\/wp-content\/uploads\/sites\/3\/2020\/12\/HeadTracking_small.png\" alt=\"\" width=\"200\" height=\"105\" \/>Non<\/span><span style=\"font-size: 1rem;\">ver<\/span><span style=\"font-size: 1rem;\">b<\/span>al behaviors\u00a0<span style=\"font-size: 1rem;\">such as gestures\u00a0<\/span><span style=\"font-size: 1rem;\">and<\/span>\u00a0facial expressions are unconsciously expressed during conversations, and they function as social signals in communication. Socia<span style=\"font-size: 1rem;\">l sig<\/span><span style=\"font-size: 1rem;\">nal processing (SSP)<\/span><span style=\"font-size: 1rem;\">\u00a0is<\/span><span style=\"font-size: 1rem;\">\u00a0a\u00a0research field of artificial intelligence that\u00a0<\/span><span style=\"font-size: 1rem;\">analyzes and learns models for social signals in human-to-human a<\/span><span style=\"font-size: 1rem;\">nd human-to-agent\/robot communications. Applying multimodal machine learning approach to social signals, we are devel<\/span><span style=\"font-size: 1rem;\">oping methods for estimating the characteristics of conversation participants, such as conversational engagement, leadership and communication\u00a0<\/span><span style=\"font-size: 1rem;\">skills in group discussions, and detecting important utterances in di<\/span><span style=\"font-size: 1rem;\">scussi<\/span><span style=\"font-size: 1rem;\">ons.\u00a0<\/span><\/p>\n<h3>Human-Agent Interaction<\/h3>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"size-medium wp-image-27 alignright\" src=\"https:\/\/iui.ci.seikei.ac.jp\/en\/wp-content\/uploads\/sites\/3\/2020\/12\/360a58d896ee29e31298322fef0c567a-300x220-300x220.png\" alt=\"\" width=\"300\" height=\"220\" \/>In order to realize virtual agents and robots that communicate with humans, it is necessary to generate both verbal and nonverbal behaviors of the humanoids. In particular, nonverbal behavior generation includes producing various types of behaviors such as gestures, facial expressions, and postures. We are developing technologies for generating nonverbal behaviors based on the content and the context of the dialogue and the characteristics of the speaker. We are also developing multimodal dialogue systems such as listener agents and customer service robots in robot cafes.<\/p>\n<h3>Communication support technologies<\/h3>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"size-medium wp-image-26 alignright\" src=\"https:\/\/iui.ci.seikei.ac.jp\/en\/wp-content\/uploads\/sites\/3\/2020\/12\/7b4b3ae3fcdd9ff38b58dfa28b110a98-300x150-300x150.png\" alt=\"\" width=\"300\" height=\"150\" \/><img loading=\"lazy\" decoding=\"async\" class=\"size-full wp-image-36 alignright\" src=\"https:\/\/iui.ci.seikei.ac.jp\/en\/wp-content\/uploads\/sites\/3\/2020\/12\/DiscussionBrowser_small.png\" alt=\"\" width=\"200\" height=\"102\" \/>As an application of social signal processing and conversational agent technology, we are developing communication support technologies. We have developed systems that visualize characteristics of communication and social signals, and have been investigating the effects of intervening into human conversations by computer systems.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Social signal processing Nonverbal behaviors\u00a0such as gestures\u00a0and\u00a0facial expressions are unconsciously expressed during conversations, and they function as social signals in communication. Social signal processing (SSP)\u00a0is\u00a0a\u00a0research field of artificial intelligence that\u00a0analyzes and learns models for social signals in human-to-human and human-to-agent\/robot communications. Applying multimodal machine learning approach to social signals, we are developing methods for estimating [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-10","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/iui.ci.seikei.ac.jp\/en\/wp-json\/wp\/v2\/pages\/10","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/iui.ci.seikei.ac.jp\/en\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/iui.ci.seikei.ac.jp\/en\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/iui.ci.seikei.ac.jp\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/iui.ci.seikei.ac.jp\/en\/wp-json\/wp\/v2\/comments?post=10"}],"version-history":[{"count":11,"href":"https:\/\/iui.ci.seikei.ac.jp\/en\/wp-json\/wp\/v2\/pages\/10\/revisions"}],"predecessor-version":[{"id":24,"href":"https:\/\/iui.ci.seikei.ac.jp\/en\/wp-json\/wp\/v2\/pages\/10\/revisions\/24"}],"wp:attachment":[{"href":"https:\/\/iui.ci.seikei.ac.jp\/en\/wp-json\/wp\/v2\/media?parent=10"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}