{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T22:04:21Z","timestamp":1774476261992,"version":"3.50.1"},"reference-count":28,"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\/apsipaasc63619.2025.10849063","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":1,"title":["Disentangling Speaker Representations from Intuitive Prosodic Features for Speaker-Adaptative and Prosody-Controllable Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Pengyu","family":"Cheng","sequence":"first","affiliation":[{"name":"Xiaomi Inc.,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenhua","family":"Ling","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,NERC-SLIP,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Meng","sequence":"additional","affiliation":[{"name":"Xiaomi Inc.,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujun","family":"Wang","sequence":"additional","affiliation":[{"name":"Xiaomi Inc.,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref2","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"International Conference on Learning Representations","author":"Ren"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref4","article-title":"Wavenet: A generative model for raw audio","author":"Oord","year":"2016"},{"key":"ref5","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"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1558"},{"key":"ref7","first-page":"3683","article-title":"Fitting new speakers based on a short untranscribed sample","volume-title":"International Conference on Machine Learning","author":"Nachmani"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-5"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1705"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref11","first-page":"4485","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume":"31","author":"Jia","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","article-title":"Neural voice cloning with a few samples","author":"Arik","year":"2018"},{"key":"ref13","article-title":"Sample efficient adaptive text-to-speech","author":"Chen","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053104"},{"key":"ref15","article-title":"Modeling multi-speaker latent space to improve neural tts: Quick enrolling new speaker and enhancing premium voice","author":"Deng","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413396"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3529570.3529602"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2861"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2918"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054556"},{"key":"ref21","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413398"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-755"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2980991"},{"issue":"1","key":"ref25","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"The journal of machine learning research"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461829"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"}],"event":{"name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","location":"Macau, Macao","start":{"date-parts":[[2024,12,3]]},"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\/10849063.pdf?arnumber=10849063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:24:19Z","timestamp":1738045459000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10849063\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc63619.2025.10849063","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}