{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T05:27:19Z","timestamp":1738128439670,"version":"3.33.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2024,12,3]]},"DOI":"10.1109\/apsipaasc63619.2025.10848787","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:37:05Z","timestamp":1738003025000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["StylebookTTS: Zero-Shot Text-to-Speech Leveraging Unsupervised Style Representation"],"prefix":"10.1109","author":[{"given":"Juhwan","family":"Yoon","sequence":"first","affiliation":[{"name":"Yonsei University,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyungseob","family":"Lim","sequence":"additional","affiliation":[{"name":"Yonsei University,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyeonjin","family":"Cha","sequence":"additional","affiliation":[{"name":"Yonsei University,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong-Goo","family":"Kang","sequence":"additional","affiliation":[{"name":"Yonsei University,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"article-title":"Stylebook: Content-dependent speaking style modeling for any-to-any voice conversion using only speech data","year":"2023","author":"Lim","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Ren","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Proc. Advances in neural information processing systems (NeurIPS)","author":"Ren","key":"ref7"},{"article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. International Conference on Machine Learning (ICML)","author":"Kim","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1774"},{"article-title":"Yourtts: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone","volume-title":"Proc. International Conference on Machine Learning (ICML)","author":"Casanova","key":"ref10"},{"key":"ref11","first-page":"7748","article-title":"Meta-stylespeech: Multi-speaker adaptive text-to-speech generation","volume-title":"Proc. International Conference on Machine Learning (ICML)","author":"Min"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2326"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10054"},{"article-title":"Neural codec language models are zero-shot text to speech synthesizers","year":"2023","author":"Wang","key":"ref14"},{"article-title":"P-flow: A fast and data-efficient zero-shot tts through speech prompting","volume-title":"Proc. Advances in Neural Information Processing Systems (NeurIPS)","author":"Kim","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29747"},{"article-title":"NaturalSpeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Shen","key":"ref17"},{"article-title":"Score-based generative mod-eling through stochastic differential equations","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Song","key":"ref18"},{"article-title":"Attention is all you need","volume-title":"Proc. Advances in neural information processing systems (NIPS)","author":"Vaswani","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"article-title":"Diffusion-based voice conversion with fast maximum likelihood sampling scheme","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Popov","key":"ref22"},{"article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","year":"2020","author":"Kong","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"journal-title":"Method for the subjective assessment of small impairments in audio systems. Rec. ITU-R BS.1116-3","year":"2015","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"}],"event":{"name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2024,12,3]]},"location":"Macau, Macao","end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10848542\/10848533\/10848787.pdf?arnumber=10848787","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:10:17Z","timestamp":1738044617000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10848787\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc63619.2025.10848787","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}