{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T17:20:27Z","timestamp":1765041627583,"version":"3.33.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832278","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"698-704","source":"Crossref","is-referenced-by-count":3,"title":["Disentangling The Prosody And Semantic Information With Pre-Trained Model For In-Context Learning Based Zero-Shot Voice Conversion"],"prefix":"10.1109","author":[{"given":"Zhengyang","family":"Chen","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuechen","family":"Liu","sequence":"additional","affiliation":[{"name":"National Institute of Informatics,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[{"name":"National Institute of Informatics,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2412"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096471"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref4","first-page":"16251","article-title":"Neural analysis and synthesis: Reconstructing speech from self-supervised representations","volume":"34","author":"Choi","year":"2021","journal-title":"Ad vances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413699"},{"key":"ref6","first-page":"25","article-title":"Retriever: Learning content-style representation as a token-level bipartite graph","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event","author":"Yin"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3379877"},{"key":"ref9","article-title":"Nguyen Trung Hieu, Jia Qi Yip, and Bin Ma, Phonetic enhanced language modeling for text-to-speech synthesis","author":"Zhou","year":"2024","journal-title":"arXiv preprint arXiv:2406.02009"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447751"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447296"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3451951"},{"key":"ref13","article-title":"Ham-tts: Hierarchical acoustic modeling for token-based zeroshot text-to-speech with model and data scaling","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv:2403.05989"},{"key":"ref14","first-page":"5210","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","volume-title":"International Conference on Machine Learning","author":"Qian"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1584"},{"key":"ref18","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2301.02111"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29747"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3362\/0262-8104.2002.009"},{"key":"ref21","article-title":"Seed-tts: A family of high-quality versatile speech generation models","author":"Anastassiou","year":"2024","journal-title":"arXiv preprint arXiv:2406.02430"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.931"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref24","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-489"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054734"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-363"},{"key":"ref28","article-title":"Towards human-like spoken dialogue generation between ai agents from written dialogue","author":"Mitsui","year":"2023","journal-title":"arXiv preprint arXiv:2310.01088"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1508"},{"article-title":"Flow matching for generative modeling","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Lipman","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref33","article-title":"Vocos: Closing the gap between time-domain and fourier-based neural vocoders for high-quality audio synthesis","author":"Siuzdak","year":"2023","journal-title":"arXiv preprint arXiv:2306.00814"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747814"},{"key":"ref36","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":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096626"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3439996"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094850"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096057"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2024,12,2]]},"location":"Macao","end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832278.pdf?arnumber=10832278","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:39:23Z","timestamp":1737398363000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832278\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832278","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}