{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T14:55:00Z","timestamp":1726239300996},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819987146"},{"type":"electronic","value":"9789819987153"}],"license":[{"start":{"date-parts":[[2023,12,3]],"date-time":"2023-12-03T00:00:00Z","timestamp":1701561600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,3]],"date-time":"2023-12-03T00:00:00Z","timestamp":1701561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,3]],"date-time":"2023-12-03T00:00:00Z","timestamp":1701561600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,3]],"date-time":"2023-12-03T00:00:00Z","timestamp":1701561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-99-8715-3_8","type":"book-chapter","created":{"date-parts":[[2023,12,2]],"date-time":"2023-12-02T08:02:08Z","timestamp":1701504128000},"page":"80-93","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GERT: Transformers for\u00a0Co-speech Gesture Prediction in\u00a0Social Robots"],"prefix":"10.1007","author":[{"ORCID":"http:\/\/orcid.org\/0000-0001-9214-4973","authenticated-orcid":false,"given":"Javier","family":"Sevilla-Salcedo","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0001-5763-2015","authenticated-orcid":false,"given":"Enrique","family":"Fern\u00e1ndez-Rodicio","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-0454-9466","authenticated-orcid":false,"given":"Jos\u00e9 Carlos","family":"Castillo","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-5189-0002","authenticated-orcid":false,"given":"\u00c1lvaro","family":"Castro-Gonz\u00e1lez","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-0263-6606","authenticated-orcid":false,"given":"Miguel A.","family":"Salichs","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,3]]},"reference":[{"doi-asserted-by":"publisher","unstructured":"Ahuja, C., Lee, D.W., Nakano, Y.I., Morency, L.-P.: Style transfer for co-speech gesture animation: a multi-speaker conditional-mixture approach. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12363, pp. 248\u2013265. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58523-5_15","key":"8_CR1","DOI":"10.1007\/978-3-030-58523-5_15"},{"unstructured":"Baevski, A., Auli, M.: Robust speech recognition via large-scale weak supervision. arXiv preprint arXiv:2206.04541 (2022)","key":"8_CR2"},{"doi-asserted-by":"crossref","unstructured":"Bartneck, C., Kanda, T., Mubin, O., Mahmud, A.: Does the design of a robot influence its animacy and perceived intelligence? Int. J. Soc. Robot. 1, 195\u2013204 (2009)","key":"8_CR3","DOI":"10.1007\/s12369-009-0013-7"},{"doi-asserted-by":"crossref","unstructured":"Chang, C.J., Zhang, S., Kapadia, M.: The IVI lab entry to the Genea challenge 2022-a tacotron2 based method for co-speech gesture generation with locality-constraint attention mechanism. In: Proceedings of the 2022 International Conference on Multimodal Interaction, pp. 784\u2013789 (2022)","key":"8_CR4","DOI":"10.1145\/3536221.3558060"},{"unstructured":"Chiu, C.C., Marsella, S.: Gesture generation with low-dimensional embeddings. In: Proceedings of the 2014 International Conference on Autonomous Agents and Multi-agent Systems, pp. 781\u2013788 (2014)","key":"8_CR5"},{"doi-asserted-by":"publisher","unstructured":"Chiu, C.-C., Morency, L.-P., Marsella, S.: Predicting co-verbal gestures: a deep and temporal modeling approach. In: Brinkman, W.-P., Broekens, J., Heylen, D. (eds.) IVA 2015. LNCS (LNAI), vol. 9238, pp. 152\u2013166. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-21996-7_17","key":"8_CR6","DOI":"10.1007\/978-3-319-21996-7_17"},{"unstructured":"Danescu-Niculescu-Mizil, C., Lee, L.: Chameleons in imagined conversations: a new approach to understanding coordination of linguistic style in dialogs. In: Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics (ACL 2011) (2011)","key":"8_CR7"},{"unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)","key":"8_CR8"},{"doi-asserted-by":"crossref","unstructured":"Ginosar, S., Bar, A., Kohavi, G., Chan, C., Owens, A., Malik, J.: Learning individual styles of conversational gesture. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3497\u20133506 (2019)","key":"8_CR9","DOI":"10.1109\/CVPR.2019.00361"},{"doi-asserted-by":"crossref","unstructured":"Kucherenko, T., Hasegawa, D., Henter, G.E., Kaneko, N., Kjellstr\u00f6m, H.: Analyzing input and output representations for speech-driven gesture generation. In: Proceedings of the 19th ACM International Conference on Intelligent Virtual Agents, pp. 97\u2013104 (2019)","key":"8_CR10","DOI":"10.1145\/3308532.3329472"},{"doi-asserted-by":"crossref","unstructured":"Kucherenko, T., Nagy, R., Jonell, P., Neff, M., Kjellstr\u00f6m, H., Henter, G.E.: Speech2properties2gestures: gesture-property prediction as a tool for generating representational gestures from speech. In: Proceedings of the 21st ACM International Conference on Intelligent Virtual Agents, pp. 145\u2013147 (2021)","key":"8_CR11","DOI":"10.1145\/3472306.3478333"},{"unstructured":"Li, R., Wang, Z., Wu, Y., Zhu, Y., Liu, C.L., Yang, Y.: Diffusion models beat GANS on image synthesis. arXiv preprint arXiv:2105.05233 (2021)","key":"8_CR12"},{"doi-asserted-by":"crossref","unstructured":"Liang, Y., Feng, Q., Zhu, L., Hu, L., Pan, P., Yang, Y.: SEEG: semantic energized co-speech gesture generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10473\u201310482 (2022)","key":"8_CR13","DOI":"10.1109\/CVPR52688.2022.01022"},{"unstructured":"Liu, Y., et al.: Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)","key":"8_CR14"},{"doi-asserted-by":"publisher","unstructured":"Mart\u00edn Galv\u00e1n, L., Fern\u00e1ndez-Rodicio, E., Sevilla Salcedo, J., Castro-Gonz\u00e1lez, \u00c1., Salichs, M.A.: Using deep learning for implementing paraphrasing in a social robot. In: Juli\u00e1n, V., Carneiro, J., Alonso, R.S., Chamoso, P., Novais, P. (eds.) Ambient Intelligence-Software and Applications\u201313th International Symposium on Ambient Intelligence. LNNS, vol. 603, pp. 219\u2013228. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-22356-3_21","key":"8_CR15","DOI":"10.1007\/978-3-031-22356-3_21"},{"unstructured":"Microsoft: Bing chat (2023). https:\/\/www.bing.com\/","key":"8_CR16"},{"doi-asserted-by":"crossref","unstructured":"Miller, R.B.: Response time in man-computer conversational transactions. In: Proceedings of the Fall Joint Computer Conference, 9\u201311 December 1968, Part I, pp. 267\u2013277 (1968)","key":"8_CR17","DOI":"10.1145\/1476589.1476628"},{"unstructured":"Nakayama, H.: seqeval: a python framework for sequence labeling evaluation. Software available (2018). https:\/\/github.com\/chakki-works\/seqeval","key":"8_CR18"},{"unstructured":"Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","key":"8_CR19"},{"doi-asserted-by":"crossref","unstructured":"P\u00e9rez-Mayos, L., Farr\u00fas, M., Adell, J.: Part-of-speech and prosody-based approaches for robot speech and gesture synchronization. J. Intell. Robot. Syst. 1\u201311 (2019)","key":"8_CR20","DOI":"10.1007\/s10846-019-01100-3"},{"issue":"10","key":"8_CR21","doi-asserted-by":"publisher","first-page":"1943","DOI":"10.1177\/0956797614547706","volume":"25","author":"KE Powers","year":"2014","unstructured":"Powers, K.E., Worsham, A.L., Freeman, J.B., Wheatley, T., Heatherton, T.F.: Social connection modulates perceptions of animacy. Psychol. Sci. 25(10), 1943\u20131948 (2014)","journal-title":"Psychol. Sci."},{"doi-asserted-by":"crossref","unstructured":"Rosenthal-von der P\u00fctten, A.M., Kr\u00e4mer, N.C., Herrmann, J.: The effects of humanlike and robot-specific affective nonverbal behavior on perception, emotion, and behavior. Int. J. Soc. Robot. 10(5), 569\u2013582 (2018)","key":"8_CR22","DOI":"10.1007\/s12369-018-0466-7"},{"unstructured":"Quigley, M., et al.: ROS: an open-source robot operating system. In: ICRA Workshop on Open Source Software, Kobe, vol. 3, p. 5 (2009)","key":"8_CR23"},{"unstructured":"Radford, A., et al.: Improving language understanding by generative pre-training (2018)","key":"8_CR24"},{"doi-asserted-by":"crossref","unstructured":"Salichs, M.A., et al.: Mini: a new social robot for the elderly. Int. J. Soc. Robot. 12, 1231\u20131249 (2020)","key":"8_CR25","DOI":"10.1007\/s12369-020-00687-0"},{"unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)","key":"8_CR26"},{"doi-asserted-by":"publisher","unstructured":"Sevilla Salcedo, J., Mart\u00edn Galv\u00e1n, L., Castillo, J.C., Castro-Gonz\u00e1lez, \u00c1., Salichs, M.A.: User-adapted semantic description generation using natural language models. In: Juli\u00e1n, V., Carneiro, J., Alonso, R.S., Chamoso, P., Novais, P. (eds.) Ambient Intelligence\u2014Software and Applications, ISAmI 2022. LNNS, vol. 603, pp. 134\u2013144. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-22356-3_13","key":"8_CR27","DOI":"10.1007\/978-3-031-22356-3_13"},{"doi-asserted-by":"crossref","unstructured":"Shiwa, T., Kanda, T., Imai, M., Ishiguro, H., Hagita, N.: How quickly should communication robots respond? In: 2008 3rd ACM\/IEEE International Conference on Human-Robot Interaction (HRI), pp. 153\u2013160. IEEE (2008)","key":"8_CR28","DOI":"10.1145\/1349822.1349843"},{"unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)","key":"8_CR29"},{"doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: GLUE: a multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461v3 (2018)","key":"8_CR30","DOI":"10.18653\/v1\/W18-5446"},{"doi-asserted-by":"crossref","unstructured":"Yoon, Y., Ko, W.R., Jang, M., Lee, J., Kim, J., Lee, G.: Robots learn social skills: end-to-end learning of co-speech gesture generation for humanoid robots. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 4303\u20134309. IEEE (2019)","key":"8_CR31","DOI":"10.1109\/ICRA.2019.8793720"}],"container-title":["Lecture Notes in Computer Science","Social Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8715-3_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,2]],"date-time":"2023-12-02T09:08:59Z","timestamp":1701508139000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8715-3_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,3]]},"ISBN":["9789819987146","9789819987153"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8715-3_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,3]]},"assertion":[{"value":"3 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICSR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Social Robotics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Doha","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Qatar","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 December 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 December 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"socrob2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icrs.iovision.tn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EquinOCS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"83","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"68","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"82% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}