{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:01:38Z","timestamp":1764399698663,"version":"3.46.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249248","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"956-961","source":"Crossref","is-referenced-by-count":0,"title":["Improving Listening Head Generation Performance Using Speech Representations from Self-Supervised Learning"],"prefix":"10.1109","author":[{"given":"Tamon","family":"Mikawa","sequence":"first","affiliation":[{"name":"Toyohashi University of Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasuhisa","family":"Fujii","sequence":"additional","affiliation":[{"name":"Toyohashi University of Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yukoh","family":"Wakabayashi","sequence":"additional","affiliation":[{"name":"Google DeepMind,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kengo","family":"Ohta","sequence":"additional","affiliation":[{"name":"Toyohashi University of Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryota","family":"Nishimura","sequence":"additional","affiliation":[{"name":"National Institute of Technology, Anan College,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Norihide","family":"Kitaoka","sequence":"additional","affiliation":[{"name":"Toyohashi University of Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1111\/j.0963-7214.2004.01502010.x"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.2002.1004186"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3041672"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33197-8_41"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_8"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023234"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887862"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01251-8"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206665"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383315"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/11550617_3"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2014-186"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-137"},{"volume-title":"Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition","year":"2014","author":"Sak","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-894"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref19","first-page":"13898","article-title":"Release of pre-trained models for the Japanese language","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)","author":"Sawada"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01975"},{"journal-title":"Real-time facial surface geometry from monocular video on mobile gpus","year":"2019","author":"Kartynnik","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"journal-title":"Decoupled weight decay regularization","year":"2019","author":"Loshchilov","key":"ref23"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249248.pdf?arnumber=11249248","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:59:01Z","timestamp":1764399541000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249248\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249248","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}