{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T07:27:29Z","timestamp":1768030049434,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,11,5]],"date-time":"2018-11-05T00:00:00Z","timestamp":1541376000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,11,5]]},"DOI":"10.1145\/3267851.3267866","type":"proceedings-article","created":{"date-parts":[[2018,11,21]],"date-time":"2018-11-21T14:02:20Z","timestamp":1542808940000},"page":"87-92","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["Generating Body Motions using Spoken Language in Dialogue"],"prefix":"10.1145","author":[{"given":"Ryo","family":"Ishii","sequence":"first","affiliation":[{"name":"NTT Media Intelligence Laboratories, NTT Corporation, Yokosuka-shi, Kanagawa, Japan"}]},{"given":"Taichi","family":"Katayama","sequence":"additional","affiliation":[{"name":"NTT Media Intelligence Laboratories, NTT Corporation, Yokosuka-shi, Kanagawa, Japan"}]},{"given":"Ryuichiro","family":"Higashinaka","sequence":"additional","affiliation":[{"name":"NTT Media Intelligence Laboratories, NTT Corporation, Yokosuka-shi, Kanagawa, Japan"}]},{"given":"Junji","family":"Tomita","sequence":"additional","affiliation":[{"name":"NTT Media Intelligence Laboratories, NTT Corporation, Yokosuka-shi, Kanagawa, Japan"}]}],"member":"320","published-online":{"date-parts":[[2018,11,5]]},"reference":[{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Jonas Beskow Bjorn Granstrom and David House. 2006. Visual correlates to prominence in several expressive modes. In INTERSPEECH.  Jonas Beskow Bjorn Granstrom and David House. 2006. Visual correlates to prominence in several expressive modes. In INTERSPEECH.","DOI":"10.21437\/Interspeech.2006-375"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Ray L. BirdWhistell. 1970. Kinesics and context. University of Pennsylvania Press.  Ray L. BirdWhistell. 1970. Kinesics and context. University of Pennsylvania Press.","DOI":"10.9783\/9780812201284"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.885910"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383315"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"C.-C Chiu L.-P Morency and Stacy Marsella. 2015. Predicting Co-verbal Gestures: A Deep and Temporal Modeling Approach. 152--166 pages.  C.-C Chiu L.-P Morency and Stacy Marsella. 2015. Predicting Co-verbal Gestures: A Deep and Temporal Modeling Approach. 152--166 pages.","DOI":"10.1007\/978-3-319-21996-7_17"},{"key":"e_1_3_2_1_7_1","unstructured":"NTT TechnoCross Corporation. 2018. FutureVoice. http:\/\/www.v-series.jp\/futurevoice\/  NTT TechnoCross Corporation. 2018. FutureVoice. http:\/\/www.v-series.jp\/futurevoice\/"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.3115\/980845.980915"},{"key":"e_1_3_2_1_9_1","volume-title":"Visual Prosody: Facial Movements Accompanying Speech. In IEEE International Conference on Automatic Face and Gesture Recognition. 381--386","author":"Graf Hans Peter","year":"2002"},{"key":"e_1_3_2_1_10_1","volume-title":"International conference on Computational linguistics. 928--939","author":"Higashinaka Ryuichiro","year":"2014"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2007.4399335"},{"key":"e_1_3_2_1_12_1","volume-title":"ACM\/IEEE International Conference on Human-Robot Interaction. 293--300","author":"Ishi Carlos T.","year":"2010"},{"key":"e_1_3_2_1_13_1","volume-title":"6th International Conference (IVA'06)","author":"Ishii Ryo"},{"key":"e_1_3_2_1_14_1","volume-title":"International Conference on spoken language. 2167--2170","author":"Iwano Y."},{"key":"e_1_3_2_1_15_1","volume-title":"Generating Iconic Gestures Based on Graphic Data Analysis and Clustering. In The Eleventh ACM\/IEEE International Conference on Human Robot Interaction (HRI '16)","author":"Kadono Yuki"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Munhall KG Jones JA Callan DE Kuratate T and Vatikiotis-Bateson E. 2004. Visual prosody and speech intelligibility: head movement improves auditory speech perception. 15 2 (2004) 133--7.  Munhall KG Jones JA Callan DE Kuratate T and Vatikiotis-Bateson E. 2004. Visual prosody and speech intelligibility: head movement improves auditory speech perception. 15 2 (2004) 133--7.","DOI":"10.1111\/j.0963-7214.2004.01502010.x"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1177\/002383099804100404"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556288.2557274"},{"key":"e_1_3_2_1_19_1","unstructured":"David McNeill. 1996. Hand and Mind: What Gestures Reveal About Thought. University Of Chicago Press.  David McNeill. 1996. Hand and Mind: What Gestures Reveal About Thought. University Of Chicago Press."},{"key":"e_1_3_2_1_20_1","volume-title":"International conference on computational linguistics. 761--769","author":"Meguro Toyomi","year":"2010"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Yukiko I. Nakano Masashi Okamoto Daisuke Kawahara Qing Li and Toyoaki Nishida. 2004. Converting Text into Agent Animations: Assigning Gestures to Text. 4 pages.  Yukiko I. Nakano Masashi Okamoto Daisuke Kawahara Qing Li and Toyoaki Nishida. 2004. Converting Text into Agent Animations: Assigning Gestures to Text. 4 pages.","DOI":"10.3115\/1613984.1614023"},{"key":"e_1_3_2_1_22_1","unstructured":"Ekman Paul Friesen Wallace and Hager Joseph. 2002. Facial action coding system: a technique for the measurement of facial movement. Consulting Psychologists Press.  Ekman Paul Friesen Wallace and Hager Joseph. 2002. Facial action coding system: a technique for the measurement of facial movement. Consulting Psychologists Press."},{"key":"e_1_3_2_1_23_1","unstructured":"Florian Schroff Dmitry Kalenichenko and James Philbin. 2015. FaceNet: A Unified Embedding for Face Recognition and Clustering. CoRR abs\/1503.03832 (2015). arXiv:1503.03832 http:\/\/arxiv.org\/abs\/1503.03832  Florian Schroff Dmitry Kalenichenko and James Philbin. 2015. FaceNet: A Unified Embedding for Face Recognition and Clustering. CoRR abs\/1503.03832 (2015). arXiv:1503.03832 http:\/\/arxiv.org\/abs\/1503.03832"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/0378-2166(87)90181-0"},{"key":"e_1_3_2_1_25_1","unstructured":"Senko Maynard. 1989. Japanese conversation: Self-contextualization through structure and interactional management. Norwood New Jersey: Ablex Publishing Corporation (1989).  Senko Maynard. 1989. Japanese conversation: Self-contextualization through structure and interactional management. Norwood New Jersey: Ablex Publishing Corporation (1989)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.09.008"},{"key":"e_1_3_2_1_27_1","volume-title":"International Conference on Language Resources and Evaluation.","author":"Wittenburg P.","year":"2006"},{"key":"e_1_3_2_1_28_1","volume-title":"HCI","author":"Yamamoto Michiya"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Hani Camille Yehia Takaaki Kuratate and Eric Vatikiotis-Bateson. 2002. Linking facial animation head motion and speech acoustics. 30 3 (2002) 555--568.  Hani Camille Yehia Takaaki Kuratate and Eric Vatikiotis-Bateson. 2002. Linking facial animation head motion and speech acoustics. 30 3 (2002) 555--568.","DOI":"10.1006\/jpho.2002.0165"}],"event":{"name":"IVA '18: International Conference on Intelligent Virtual Agents","location":"Sydney NSW Australia","acronym":"IVA '18","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence"]},"container-title":["Proceedings of the 18th International Conference on Intelligent Virtual Agents"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3267851.3267866","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3267851.3267866","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:43:58Z","timestamp":1750207438000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3267851.3267866"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,5]]},"references-count":28,"alternative-id":["10.1145\/3267851.3267866","10.1145\/3267851"],"URL":"https:\/\/doi.org\/10.1145\/3267851.3267866","relation":{},"subject":[],"published":{"date-parts":[[2018,11,5]]},"assertion":[{"value":"2018-11-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}