{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:28:53Z","timestamp":1763191733087,"version":"3.45.0"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228511","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["V-CASS: Vision-context-aware Expressive Speech Synthesis for Enhancing User Understanding of Videos"],"prefix":"10.1109","author":[{"given":"Qixin","family":"Wang","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China"}]},{"given":"Songtao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China"}]},{"given":"Zeyu","family":"Jin","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China"}]},{"given":"Chenglin","family":"Guo","sequence":"additional","affiliation":[{"name":"New York University,Stern School of Business,New York,USA"}]},{"given":"Shikun","family":"Sun","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China"}]},{"given":"Xiaoyu","family":"Qin","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3117472"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-021-00487-x"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3042484"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-023-00290-x"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(02)00084-5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0264356"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3758\/s13414-021-02334-w"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546396.025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s42761-021-00049-7"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.29"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/0264619618794750"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ics.2005.05.215"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2018.02685"},{"volume-title":"Colorist: a practical handbook for personal and professional use","year":"1998","author":"Kobayasi","key":"ref14"},{"volume-title":"Film art: an introduction","year":"2013","author":"Bordwell","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"article-title":"WaveNet: A Generative Model for Raw Audio","year":"2016","author":"Oord","key":"ref17"},{"key":"ref18","first-page":"19 594","article-title":"Styletts 2: Towards human-level text-to-speech through style diffusion and adversarial training with large speech language models","volume":"36","author":"Li","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","first-page":"2709","article-title":"Yourtts: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone","volume-title":"International conference on machine learning","author":"Casanova"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3402088"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681680"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445879"},{"article-title":"PromptTTS 2: Describing and Generating Voices with Text Prompt","year":"2023","author":"Leng","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26628"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29769"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2136"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094745"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475198"},{"article-title":"EALD-MLLM: Emotion Analysis in Long-sequential and De-identity videos with Multi-modal Large Language Model","year":"2024","author":"Li","key":"ref31"},{"article-title":"Prompt-to-Prompt Image Editing with Cross Attention Control","year":"2022","author":"Hertz","key":"ref32"},{"article-title":"On the Opportunities and Risks of Foundation Models","year":"2021","author":"B","key":"ref33"},{"article-title":"Learning Transferable Visual Models From Natural Language Supervision","year":"2021","author":"Radford","key":"ref34"},{"article-title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","year":"2021","author":"Kim","key":"ref35"},{"article-title":"Video (language) modeling: a baseline for generative models of natural videos","year":"2014","author":"Ranzato","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.723"},{"key":"ref38","first-page":"24 824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3005033"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00985"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1026"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02537"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1080\/13645579.2020.1766777"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/BF02686918"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s12144-014-9219-4"},{"year":"2023","key":"ref46","article-title":"Gemini: A Family of Highly Capable Multimodal Models"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228511.pdf?arnumber=11228511","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:27:29Z","timestamp":1763191649000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228511\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228511","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}