{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T12:27:43Z","timestamp":1744633663434,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789811955372"},{"type":"electronic","value":"9789811955389"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-981-19-5538-9_9","type":"book-chapter","created":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T11:02:45Z","timestamp":1667214165000},"page":"133-141","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Multimodal Dialogue Response Timing Estimation Using Dialogue Context Encoder"],"prefix":"10.1007","author":[{"given":"Ryota","family":"Yahagi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuya","family":"Chiba","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takashi","family":"Nose","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akinori","family":"Ito","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,1]]},"reference":[{"unstructured":"Adiwardana D, Luong MT, So D, et\u00a0al (2020) Towards a human-like open-domain chatbot, pp 1\u201338. arXiv:2001.09977","key":"9_CR1"},{"doi-asserted-by":"crossref","unstructured":"Baltru\u0161aitis T, Robinson P, Morency LP (2016) OpenFace: an open source facial behavior analysis toolkit. In: Proceedings of IEEE winter conference on applications of computer vision, pp 1\u201310","key":"9_CR2","DOI":"10.1109\/WACV.2016.7477553"},{"unstructured":"Devlin J, Chang, MW, Lee K, Toutanova K (2018) BERT: Pre-training of deep bidirectional transformers for language understanding, pp 1\u201316. arXiv:1810.04805","key":"9_CR3"},{"doi-asserted-by":"crossref","unstructured":"Duncan S (1974) On the structure of speaker-auditor interaction during speaking turns. Language in Society, pp 161\u2013180","key":"9_CR4","DOI":"10.1017\/S0047404500004322"},{"doi-asserted-by":"crossref","unstructured":"Duncan S, Fiske D (2015) Face-to-face interaction: research, methods, and theory. Routledge","key":"9_CR5","DOI":"10.4324\/9781315660998"},{"issue":"2","key":"9_CR6","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/TAFFC.2015.2457417","volume":"7","author":"F Eyben","year":"2015","unstructured":"Eyben F, Scherer K, Schuller B et al (2015) The Geneva minimalistic acoustic parameter set (GeMAPS) for voice research and affective computing. IEEE Trans. Affect. Comput. 7(2):190\u2013202","journal-title":"IEEE Trans. Affect. Comput."},{"doi-asserted-by":"crossref","unstructured":"Fujiwara N, Itoh T, Araki K (2007) Analysis of changes in dialogue rhythm due to dialogue acts in Task-Oriented dialogues. In: Proceedings of international conference on text, speech and dialogue, pp 564\u2013573","key":"9_CR7","DOI":"10.1007\/978-3-540-74628-7_73"},{"doi-asserted-by":"crossref","unstructured":"Ji Y, Haffari G, Eisenstein J (2016) A latent variable recurrent neural network for discourse-driven language models. In: Proceedings of NAACL-HLT, pp 332\u2013342","key":"9_CR8","DOI":"10.18653\/v1\/N16-1037"},{"unstructured":"Joulin A, Grave E, Bojanowski P, Douze M, J\u00e9gou H, Mikolov T (2016) FastText. zip: compressing text classification models, pp 1\u201313. arXiv:1612.03651","key":"9_CR9"},{"key":"9_CR10","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/0001-6918(67)90005-4","volume":"26","author":"A Kendon","year":"1967","unstructured":"Kendon A (1967) Some functions of gaze-direction in social interaction. Acta Psychol 26:22\u201363","journal-title":"Acta Psychol"},{"issue":"1","key":"9_CR11","first-page":"296","volume":"1","author":"N Kitaoka","year":"2006","unstructured":"Kitaoka N, Takeuchi M, Nishimura R, Nakagawa S (2006) Response timing detection using prosodic and linguistic information for human-friendly spoken dialog systems. Inf Media Technol 1(1):296\u2013304","journal-title":"Inf Media Technol"},{"key":"9_CR12","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/j.ijhcs.2017.02.005","volume":"103","author":"S Lee","year":"2017","unstructured":"Lee S, Choi J (2017) Enhancing user experience with conversational agent for movie recommendation: effects of self-disclosure and reciprocity. Int J Hum-Comput Stud 103:95\u2013105","journal-title":"Int J Hum-Comput Stud"},{"doi-asserted-by":"crossref","unstructured":"Li R, Lin C, Collinson M, Li X, Chen G (2019) A dual-attention hierarchical recurrent neural network for dialogue act classification. In: Proceedings of CoNLL, pp 383\u2013392","key":"9_CR13","DOI":"10.18653\/v1\/K19-1036"},{"doi-asserted-by":"crossref","unstructured":"Liu C, Ishi CT, Ishiguro H (2017) Turn-taking estimation model based on joint embedding of lexical and prosodic contents. In: Program INTERSPEECH, pp 1686\u20131690","key":"9_CR14","DOI":"10.21437\/Interspeech.2017-965"},{"doi-asserted-by":"crossref","unstructured":"Masumura R, Tanaka T, Ando A, Ishii R, Higashinaka R, Aono Y (2018) Neural dialogue context online end-of-turn detection. In: Proceedings of SIGDIAL, pp 224\u2013228","key":"9_CR15","DOI":"10.18653\/v1\/W18-5024"},{"unstructured":"Raheja V, Tetreault J (2019) Dialogue act classification with context-aware self-attention. In: Proceedings of NAACL-HLT, pp 3727\u20133733","key":"9_CR16"},{"unstructured":"Ram A, Prasad R, Khatri C, et\u00a0al (2018) Conversational AI: the science behind the Alexa Prize, pp 1\u201318. arXiv:1801.03604","key":"9_CR17"},{"doi-asserted-by":"crossref","unstructured":"Roddy M, Harte N (2020) Neural generation of dialogue response timings. In: Proceedings of ACL, pp 2442\u20132452","key":"9_CR18","DOI":"10.18653\/v1\/2020.acl-main.221"},{"doi-asserted-by":"crossref","unstructured":"Roddy M, Skantze G, Harte N (2018) Multimodal continuous turn-taking prediction using multiscale RNNs. arXiv:1808.10785","key":"9_CR19","DOI":"10.1145\/3242969.3242997"},{"doi-asserted-by":"crossref","unstructured":"Sacks H (1974) An analysis of the course of a joke\u2019s telling in conversation. In: Explorations in the ethnography of speaking. Cambridge University Press, London, pp 337\u2013353","key":"9_CR20","DOI":"10.1017\/CBO9780511611810.022"},{"doi-asserted-by":"crossref","unstructured":"Skantze G (2017) Towards a general, continuous model of turn-taking in spoken dialogue using LSTM recurrent neural networks. In: Proceedings of SIGDIAL, pp 220\u2013230","key":"9_CR21","DOI":"10.18653\/v1\/W17-5527"},{"doi-asserted-by":"crossref","unstructured":"Skantze G (2020) Turn-taking in conversational systems and human-robot interaction: a review. Comput Speech Lang 101\u2013178","key":"9_CR22","DOI":"10.1016\/j.csl.2020.101178"},{"doi-asserted-by":"crossref","unstructured":"Smith E, Williamson M, Shuster K, Weston J, Boureau YL (2020) Can you put it all together: Evaluating conversational agents\u2019 ability to blend skills, pp 1\u201310. arXiv:2004.08449","key":"9_CR23","DOI":"10.18653\/v1\/2020.acl-main.183"},{"unstructured":"Yamazaki Y, Chiba Y, Nose T, Ito A (2020) Construction and analysis of a multimodal chat-talk corpus for dialog systems considering interpersonal closeness. In: Proceedings of LREC, pp 443\u2013448","key":"9_CR24"}],"container-title":["Lecture Notes in Electrical Engineering","Conversational AI for Natural Human-Centric Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-19-5538-9_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T11:03:57Z","timestamp":1667214237000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-19-5538-9_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9789811955372","9789811955389"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-19-5538-9_9","relation":{},"ISSN":["1876-1100","1876-1119"],"issn-type":[{"type":"print","value":"1876-1100"},{"type":"electronic","value":"1876-1119"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"1 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}