{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T11:20:18Z","timestamp":1764588018326,"version":"3.37.3"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":["61425017","61773379","61603390","61771472"],"award-info":[{"award-number":["61425017","61773379","61603390","61771472"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research & Development Plan of China","award":["2017YFC0820602"],"award-info":[{"award-number":["2017YFC0820602"]}]},{"name":"State Key Program of the National Natural Science Foundation of China","award":["61831022"],"award-info":[{"award-number":["61831022"]}]},{"name":"Inria-CAS Joint Research Project","award":["173211KYSB20170061"],"award-info":[{"award-number":["173211KYSB20170061"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/taslp.2019.2935807","type":"journal-article","created":{"date-parts":[[2019,8,22]],"date-time":"2019-08-22T18:56:39Z","timestamp":1566500199000},"page":"2067-2079","source":"Crossref","is-referenced-by-count":22,"title":["Forward\u2013Backward Decoding Sequence for Regularizing End-to-End TTS"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9158-1813","authenticated-orcid":false,"given":"Yibin","family":"Zheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9437-7188","authenticated-orcid":false,"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengqi","family":"Wen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2422-4618","authenticated-orcid":false,"given":"Jiangyan","family":"Yi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learning Representations"},{"key":"ref38","first-page":"2962","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","author":"arik","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","article-title":"Close to human quality TTS with transformer","author":"li","year":"2018","journal-title":"arXiv 1809 08895"},{"key":"ref31","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","first-page":"4485","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","first-page":"4790","article-title":"Conditional image generation with pixelCNN decoders","author":"van den oord","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1046"},{"key":"ref34","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472658"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref12","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178765"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178814"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472657"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref19","article-title":"Uncovering latent style factors for expressive speech synthesis","author":"wang","year":"2017","journal-title":"arXiv 1711 00520"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683862"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2010.5684840"},{"key":"ref27","first-page":"5167","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"0","journal-title":"Proc Int Conf Mach Learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511816338"},{"key":"ref6","first-page":"601","article-title":"Automatically clustering similar units for unit selection in speech synthesis","volume":"1","author":"black","year":"1997","journal-title":"Proc Eurospeech Conf"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639682"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178817"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1121\/1.424927"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1894-4_22"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1023\/A:1025761017833"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1999.0123"},{"key":"ref20","first-page":"4700","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with Tacotron","author":"skerry-ryan","year":"0","journal-title":"Proc Int Conf Mach Learning"},{"key":"ref22","first-page":"125","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"0","journal-title":"Proc ISCA Speech Synthesis Workshop"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1160"},{"key":"ref23","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc Int Conf Learning Representations"},{"key":"ref26","first-page":"1784","article-title":"Deliberation networks: Sequence generation beyond one-pass decoding","author":"xia","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","article-title":"Achieving human parity on automatic Chinese to English news translation","author":"hassan","year":"2018","journal-title":"arXiv 1803 05567"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8817316\/08805112.pdf?arnumber=8805112","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:54:27Z","timestamp":1657745667000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8805112\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":39,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2019.2935807","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2019,12]]}}}