{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T04:12:43Z","timestamp":1752984763611,"version":"3.37.3"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"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":["61631016"],"award-info":[{"award-number":["61631016"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/icme52920.2022.9859946","type":"proceedings-article","created":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T19:45:18Z","timestamp":1661543118000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Unsupervised Quantized Prosody Representation for Controllable Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Yutian","family":"Wang","sequence":"first","affiliation":[{"name":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China"}]},{"given":"Yuankun","family":"Xie","sequence":"additional","affiliation":[{"name":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China"}]},{"given":"Kun","family":"Zhao","sequence":"additional","affiliation":[{"name":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China"}]},{"given":"Hui","family":"Wang","sequence":"additional","affiliation":[{"name":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China"}]},{"given":"Qin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053520"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003859"},{"key":"ref13","article-title":"Hierarchical generative modeling for controllable speech synthesis","author":"hsu","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref14","article-title":"Neural discrete representation learning","volume":"30","author":"van den oord","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Generating diverse high-fidelity images with vq-vae-2","volume":"32","author":"razavi","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1443"},{"key":"ref17","first-page":"2410","article-title":"Efficient neural audio synthesis","volume":"80","author":"kalchbrenner","year":"0","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref18","article-title":"Attention-based models for speech recognition","volume":"28","author":"chorowski","year":"0","journal-title":"Advances in neural information processing systems"},{"year":"0","key":"ref19"},{"key":"ref4","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"ren","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref6","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume":"80","author":"wang","year":"0","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref5","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023186"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2931673"},{"key":"ref2","first-page":"4006","article-title":"Tacotron: Towards End-to-End Speech Synthesis","author":"wang","year":"0","journal-title":"Proc Interspeech 2017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1113"},{"key":"ref1","first-page":"195","article-title":"Deep voice: Real-time neural text-to-speech","volume":"70","author":"ar?k","year":"0","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"year":"0","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1121\/1.1458024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1121\/1.1917190"},{"key":"ref24","article-title":"Reducing f0 frame error of f0 tracking algorithms under noisy conditions with an unvoiced\/voiced classification frontend","author":"chu","year":"0","journal-title":"IEEE International Conference on Acoustics"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1016\/j.specom.2007.09.003","article-title":"A method for fundamental frequency estimation and voicing decision: Application to infant utterances recorded in real acoustical environments","volume":"50","author":"tomohiro","year":"2008","journal-title":"Speech Communication"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"}],"event":{"name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2022,7,18]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2022,7,22]]}},"container-title":["2022 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9859562\/9858923\/09859946.pdf?arnumber=9859946","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T20:24:47Z","timestamp":1663619087000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9859946\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icme52920.2022.9859946","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}