{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T16:01:45Z","timestamp":1759334505349,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":16,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100020950","name":"National Science and Technology Council","doi-asserted-by":"publisher","award":["113-2813-C-155-017-E"],"award-info":[{"award-number":["113-2813-C-155-017-E"]}],"id":[{"id":"10.13039\/501100020950","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science and Technology Council","award":["NSTC114-2221-E-155-016-MY2"],"award-info":[{"award-number":["NSTC114-2221-E-155-016-MY2"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,4]]},"DOI":"10.1145\/3749859.3749868","type":"proceedings-article","created":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T15:49:35Z","timestamp":1759247375000},"page":"68-74","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Voice Chat Robot with Integrated Floating Projection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3861-0162","authenticated-orcid":false,"given":"Chia-Hsun","family":"Chiang","sequence":"first","affiliation":[{"name":"Yuan Ze University, Taoyuan, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9083-9548","authenticated-orcid":false,"given":"Sen-Kai","family":"Hsu","sequence":"additional","affiliation":[{"name":"Yuan Ze University, Taoyuan, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3036-1483","authenticated-orcid":false,"given":"Yi-Jheng","family":"Huang","sequence":"additional","affiliation":[{"name":"Yuan Ze University, Taoyuan, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1981-0359","authenticated-orcid":false,"given":"Yu-Hsuan","family":"Lin","sequence":"additional","affiliation":[{"name":"Taiwan Instrument Research Institute, National Applied Research Laboratories, Hsinchu, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,9,30]]},"reference":[{"key":"e_1_3_3_1_1_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681675"},{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00502"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351066"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Yonghui Wu Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth et al. 2023. Gemini: a family of skillful multimodal models. arXiv preprint arXiv:2312.11805. 10.48550\/arXiv.2312.11805","DOI":"10.48550\/arXiv.2312.11805"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.12720\/jait.15.3.435-445"},{"key":"e_1_3_3_1_8_2","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans and Ilya Sutskever. 2018. Improving language understanding by generative pre-training. In OpenAI Technical report."},{"key":"e_1_3_3_1_9_2","volume-title":"Fastspeech: Fast, robust and controllable text to speech. In Advances in Neural Information Processing Systems 32.","author":"Ren Yi","year":"2019","unstructured":"Yi Ren, Yangjun Ruan, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, and Tie-Yan Liu. 2019. Fastspeech: Fast, robust and controllable text to speech. In Advances in Neural Information Processing Systems 32."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1703.10135"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2402.08093"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","unstructured":"Chengyi Wang Sanyuan Chen Yu Wu Ziqiang Zhang Long Zhou Shujie Liu Zhuo Chen Yanqing Liu Huaming Wang Jinyu Li Lei He Sheng Zhao and Furu Wei. 2023. arXiv preprint arXiv:2301.02111. 10.48550\/arXiv.2301.02111","DOI":"10.48550\/arXiv.2301.02111"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3356232"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","unstructured":"Joon Son Chung Amir Jamaludin and Andrew Zisserman. 2017. You said that? arXiv preprint arXiv:1705.02966. 10.48550\/arXiv.1705.02966","DOI":"10.48550\/arXiv.1705.02966"}],"event":{"name":"IVSP 2025: 2025 7th International Conference on Image, Video and Signal Processing","acronym":"IVSP 2025","location":"Ikuta Japan"},"container-title":["Proceedings of the 2025 7th International Conference on Image, Video and Signal Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3749859.3749868","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T16:51:29Z","timestamp":1759251089000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3749859.3749868"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,4]]},"references-count":16,"alternative-id":["10.1145\/3749859.3749868","10.1145\/3749859"],"URL":"https:\/\/doi.org\/10.1145\/3749859.3749868","relation":{},"subject":[],"published":{"date-parts":[[2025,3,4]]},"assertion":[{"value":"2025-09-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}