{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T05:13:44Z","timestamp":1735103624301,"version":"3.32.0"},"reference-count":33,"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":["62171207"],"award-info":[{"award-number":["62171207"]}],"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\/iscslp63861.2024.10800185","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"229-233","source":"Crossref","is-referenced-by-count":0,"title":["Bridging Facial Imagery and Vocal Reality: Stable Diffusion-Enhanced Voice Generation"],"prefix":"10.1109","author":[{"given":"Yueqian","family":"Lin","sequence":"first","affiliation":[{"name":"Data Science Research Center, Duke Kunshan University,Kunshan"}]},{"given":"Dong","family":"Liu","sequence":"additional","affiliation":[{"name":"Data Science Research Center, Duke Kunshan University,Kunshan"}]},{"given":"Yunfei","family":"Xu","sequence":"additional","affiliation":[{"name":"Guangdong OPPO Mobile Telecommunications Corp., Ltd."}]},{"given":"Hongbin","family":"Suo","sequence":"additional","affiliation":[{"name":"Guangdong OPPO Mobile Telecommunications Corp., Ltd."}]},{"given":"Ming","family":"Li","sequence":"additional","affiliation":[{"name":"Data Science Research Center, Duke Kunshan University,Kunshan"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A survey on neural speech synthesis","volume-title":"arXiv preprint","author":"Tan","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3356232"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3139"},{"key":"ref4","article-title":"Ex-presso: A benchmark and analysis of discrete expressive speech resynthesis","volume-title":"arXiv preorint","author":"Nguyen","year":"2023"},{"key":"ref5","article-title":"Singing voice data scaling-up: An introduction to ace-opencpop and kising-v2","author":"Shi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Proc. NeurIPS","volume":"32","author":"Ren","year":"2019"},{"key":"ref7","article-title":"Neural codec language model-s are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP48485.2024.10446780","article-title":"Voxblink: X-large speaker verification dataset on camera","volume-title":"Proc. ICASSP","author":"Lin","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00713"},{"key":"ref15","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"International Conference on Learning Representations","author":"Meng","year":"2022"},{"issue":"2","key":"ref16","first-page":"3","volume":"1","author":"Ramesh","year":"2022","journal-title":"Hier-archical text -conditional image generation with clip latents"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc.ICML","author":"Radford","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022954"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096882"},{"key":"ref20","article-title":"Towards practical and efficient image-to-speech captioning with vision-language pretraining and multimodal tokens","author":"Kim","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Leveraging pretrained image-text models for improving audio-visual learning","author":"Bhati","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref23","article-title":"emotion2vec: Self-supervised pretraining for speech emotion representation","author":"Ma","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-419"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref26","article-title":"Styletts: A style-based generative model for natural and diverse text-to-speech synthesis","volume-title":"arXiv preprint","author":"Li","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref28","article-title":"Face-stylespeech: Improved face-to-voice latent mapping for natural zero-shot speech synthe-sis from a face image","author":"Kang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref29","first-page":"28492","article-title":"Robust speech recognition via large-scale weak su-pervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2023"},{"key":"ref30","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL","author":"Devlin","year":"2019"},{"key":"ref31","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094745"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095515"}],"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\/10800185.pdf?arnumber=10800185","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:26:17Z","timestamp":1735021577000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800185\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800185","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}