{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T06:58:22Z","timestamp":1775199502416,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11433839","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-4","source":"Crossref","is-referenced-by-count":0,"title":["CAVIARES: Corpus for Audio-Visual Expressive Voice Agent"],"prefix":"10.1109","author":[{"given":"Jinsheng","family":"Chen","sequence":"first","affiliation":[{"name":"The University of Tokyo,Japan"}]},{"given":"Yuki","family":"Saito","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}]},{"given":"Dong","family":"Yang","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}]},{"given":"Naoko","family":"Tanji","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}]},{"given":"Hironori","family":"Doi","sequence":"additional","affiliation":[{"name":"LY Corp.,Japan"}]},{"given":"Byeongseon","family":"Park","sequence":"additional","affiliation":[{"name":"LY Corp.,Japan"}]},{"given":"Yuma","family":"Shirahata","sequence":"additional","affiliation":[{"name":"LY Corp.,Japan"}]},{"given":"Kentaro","family":"Tachibana","sequence":"additional","affiliation":[{"name":"LY Corp.,Japan"}]},{"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-364"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"issue":"6","key":"ref4","first-page":"1","article-title":"MakeItTalk: Speaker-aware talking-head animation","volume":"39","author":"Zhou","year":"2020","journal-title":"ACM Transactions on Graphics"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00938"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_25"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054127"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref10","article-title":"MediaPipe: A framework for perceiving and processing reality","volume-title":"Proc. CVPR Workshop on CV4ARVR","author":"Lugaresi"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1098"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-300"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1250\/ast.41.761"},{"key":"ref15","article-title":"ITA Corpus","author":"Koguchi","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-105"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-205"},{"key":"ref18","article-title":"Real-time facial surface geometry from monocular video on mobile GPUs","volume-title":"Proc. CVPR Workshop on CV4ARVR","author":"Kartynnik"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.2307\/2992207"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1097-z"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref22","volume":"arXiv:2303.09797","author":"Wu","year":"2023","journal-title":"MMFace4D: A large-scale multi-modal 4D face dataset for audio-driven 3D face animation"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.09.001"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11433839.pdf?arnumber=11433839","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:54:21Z","timestamp":1775192061000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11433839\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11433839","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}