{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T05:14:42Z","timestamp":1735103682630,"version":"3.32.0"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076144"],"award-info":[{"award-number":["62076144"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,11,7]]},"DOI":"10.1109\/iscslp63861.2024.10800066","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"421-425","source":"Crossref","is-referenced-by-count":0,"title":["Inferring Agent Speaking Styles for Auditory-Visual User-Agent Conversation"],"prefix":"10.1109","author":[{"given":"Zhihan","family":"Yang","sequence":"first","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen"}]},{"given":"Chunfeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Bytedance Inc,Beijing"}]},{"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen"}]},{"given":"Jia","family":"Jia","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095751"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096905"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10338"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613823"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547831"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.115.2.268"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0032321"},{"key":"ref8","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"arXiv preprint"},{"key":"ref9","first-page":"30119","article-title":"Facial expression recognition with adaptive frame rate based on multiple testing correction","volume-title":"Proceedings of the 40th International Conference on Machine Learning (ICML), ser. Proceedings of Machine Learning Research","volume":"202","author":"Savchenko","year":"2023"},{"key":"ref10","article-title":"Bert: Pretraining of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747837"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00805"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-341"},{"key":"ref15","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2024,11,7]]},"location":"Beijing, China","end":{"date-parts":[[2024,11,10]]}},"container-title":["2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799944\/10799969\/10800066.pdf?arnumber=10800066","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:42:52Z","timestamp":1735022572000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800066\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800066","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}