{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T21:14:16Z","timestamp":1740172456725,"version":"3.37.3"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100013290","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2019YFF0303001"],"award-info":[{"award-number":["2019YFF0303001"]}],"id":[{"id":"10.13039\/501100013290","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61871358"],"award-info":[{"award-number":["61871358"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3093823","type":"journal-article","created":{"date-parts":[[2021,6,30]],"date-time":"2021-06-30T19:57:05Z","timestamp":1625083025000},"page":"2643-2655","source":"Crossref","is-referenced-by-count":4,"title":["UnitNet: A Sequence-to-Sequence Acoustic Model for Concatenative Speech Synthesis"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5263-365X","authenticated-orcid":false,"given":"Xiao","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7853-5273","authenticated-orcid":false,"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li-Rong","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"37","article-title":"Using 5\ufffdms segments in concatenative speech synthesis","author":"hirai","year":"2004","journal-title":"Proc 5th ISCA Workshop Speech Synth"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/361002.361007"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-018-1336-0"},{"key":"ref32","article-title":"The USTC system for Blizzard Challenge 2008","author":"ling","year":"2008","journal-title":"Proc Blizzard Challenge Workshop"},{"article-title":"FastSpeech 2: Fast and high-quality end-to-end text-to-speech","year":"0","author":"ren","key":"ref31"},{"key":"ref30","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"article-title":"Neural machine translation by jointly learning to align and translate","year":"0","author":"bahdanau","key":"ref37"},{"key":"ref36","first-page":"1815","article-title":"Enhancing sentence embedding with generalized pooling","author":"chen","year":"0","journal-title":"Proc 27th Int Conf Comput Linguistics (COLING 2018)"},{"key":"ref35","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref34","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","first-page":"3171","article-title":"FastSpeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"article-title":"Adam: A method for stochastic optimization","year":"0","author":"kingma","key":"ref40"},{"key":"ref11","first-page":"7586","volume":"119","author":"peng","year":"2020","journal-title":"Proc 37th Int Conf Mach Learning Ser Proc Mach Learning Research"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref15","first-page":"581","article-title":"Optimising selection of units from speech databases for concatenative synthesis","author":"black","year":"1995","journal-title":"Proc EUROSPEECH Int Speech Commun Assoc"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1978.1163055"},{"key":"ref17","first-page":"2034","article-title":"HMM-based unit selection using frame sized speech segments","author":"ling","year":"2006","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367302"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472658"},{"key":"ref28","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053812"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"ref6","first-page":"125","article-title":"WaveNet: A generative model for raw audio","author":"oord","year":"2016","journal-title":"Proc 9th ISCA Speech Synth Workshop"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1972"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054106"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref20","article-title":"The IFLYTEK system for Blizzard Challenge 2017","author":"liu","year":"2017","journal-title":"Proc Blizzard Challenge Workshop"},{"key":"ref45","article-title":"The Blizzard Challenge 2008","author":"king","year":"2008","journal-title":"Blizzard Challenge Workshop"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1798"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1107"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3233\/IDA-2007-11508"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1198"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-428"},{"key":"ref44","article-title":"Statistical analysis of the Blizzard Challenge 2007 listening test results","author":"clark","year":"2007","journal-title":"Proc BLZ3-2007"},{"key":"ref26","article-title":"The USTC system for Blizzard Challenge 2018","author":"jiang","year":"2018","journal-title":"Proc Blizzard Challenge Workshop"},{"key":"ref43","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3372244"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09468973.pdf?arnumber=9468973","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:57Z","timestamp":1652194437000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9468973\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3093823","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2021]]}}}