{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T18:55:21Z","timestamp":1742928921952,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":10,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819620739"},{"type":"electronic","value":"9789819620746"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-2074-6_21","type":"book-chapter","created":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T16:08:05Z","timestamp":1735661285000},"page":"187-193","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RoboDJ: Live Commentary Robots System Driven by\u00a0Physical- and\u00a0Cyber-World Observations"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3799-4550","authenticated-orcid":false,"given":"Yasutomo","family":"Kawanishi","sequence":"first","affiliation":[]},{"given":"Yutaka","family":"Nakamura","sequence":"additional","affiliation":[]},{"given":"Taiken","family":"Shintani","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8130-1048","authenticated-orcid":false,"given":"Carlos T.","family":"Ishi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5830-8169","authenticated-orcid":false,"given":"Seiya","family":"Kawano","sequence":"additional","affiliation":[]},{"given":"Koichiro","family":"Yoshino","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4071-1352","authenticated-orcid":false,"given":"Takashi","family":"Minato","sequence":"additional","affiliation":[]},{"given":"Michihiko","family":"Minoh","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,1,1]]},"reference":[{"key":"21_CR1","unstructured":"Development of social conversation robots CommU and Sota toward realization of a symbiotic society in which humans and robots live together. https:\/\/www.jst.go.jp\/pr\/announce\/20150120-2\/index_e.html. Accessed 13 Dec 2024"},{"key":"21_CR2","unstructured":"OpenWeatherMap API. https:\/\/openweathermap.org\/api. Accessed 13 Dec 2024"},{"key":"21_CR3","doi-asserted-by":"publisher","first-page":"25232533","DOI":"10.1109\/TASLP.2023.3288409","volume":"31","author":"Z Borsos","year":"2023","unstructured":"Borsos, Z., et al.: AudioLM: a language modeling approach to audio generation. IEEE\/ACM Trans. Audio Speech Lang. Proc. 31, 25232533 (2023). https:\/\/doi.org\/10.1109\/TASLP.2023.3288409","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Proc."},{"issue":"9","key":"21_CR4","doi-asserted-by":"publisher","first-page":"11169","DOI":"10.1109\/TPAMI.2023.3268066","volume":"45","author":"Y Cong","year":"2023","unstructured":"Cong, Y., Yang, M.Y., Rosenhahn, B.: RelTr: relation transformer for scene graph generation. IEEE Trans. Pattern Anal. Mach. Intell. 45(9), 11169\u201311183 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3268066","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR5","doi-asserted-by":"publisher","unstructured":"Ishi, C.T., Even, J., Hagita, N.: Speech activity detection and face orientation estimation using multiple microphone arrays and human position information. In: Proceedings of the 2015 IEEE\/RSJ International Conference on Intelligent Robots and Systems (2015). https:\/\/doi.org\/10.1109\/IROS.2015.7354167","DOI":"10.1109\/IROS.2015.7354167"},{"key":"21_CR6","unstructured":"Jocher, G., Chaurasia, A., Qiu, J.: Ultralytics YOLO (2023). https:\/\/github.com\/ultralytics\/ultralytics. Accessed 13 Dec 2024"},{"key":"21_CR7","doi-asserted-by":"publisher","unstructured":"Macenski, S., Foote, T., Gerkey, B., Lalancette, C., Woodall, W.: Robot operating system 2: design, architecture, and uses in the wild. Sci. Rob. 7(66), eabm6074 (2022). https:\/\/doi.org\/10.1126\/scirobotics.abm6074","DOI":"10.1126\/scirobotics.abm6074"},{"key":"21_CR8","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., Mcleavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: Proceedings of the 40th International Conference on Machine Learning, vol.\u00a0202, pp. 28492\u201328518 (2023)"},{"key":"21_CR9","doi-asserted-by":"publisher","unstructured":"Yuguchi, A., et al.: Butsukusa: a conversational mobile robot describing its own observations and internal states. In: Proceedings of the 17th ACM\/IEEE International Conference on Human-Robot Interaction (2022). https:\/\/doi.org\/10.1109\/HRI53351.2022.9889605","DOI":"10.1109\/HRI53351.2022.9889605"},{"key":"21_CR10","doi-asserted-by":"publisher","unstructured":"Zhang, Y., et al.: ByteTrack: multi-object tracking by associating every detection box. In: Proceedings of the 17th European Conference on Computer Vision (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_1","DOI":"10.1007\/978-3-031-20047-2_1"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2074-6_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T17:07:59Z","timestamp":1735664879000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2074-6_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819620739","9789819620746"],"references-count":10,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2074-6_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"1 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nara","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2025.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}