{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T10:28:21Z","timestamp":1776680901047,"version":"3.51.2"},"reference-count":22,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["2017YFB1002102"],"award-info":[{"award-number":["2017YFB1002102"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Hebei University of Economics and Business","award":["2016KYQ05"],"award-info":[{"award-number":["2016KYQ05"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2914149","type":"journal-article","created":{"date-parts":[[2019,4,30]],"date-time":"2019-04-30T16:27:42Z","timestamp":1556641662000},"page":"65955-65964","source":"Crossref","is-referenced-by-count":24,"title":["Pre-Alignment Guided Attention for Improving Training Efficiency and Model Stability in End-to-End Speech Synthesis"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8842-7329","authenticated-orcid":false,"given":"Xiaolian","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liumeng","family":"Xue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Close to human quality TTS with transformer","author":"li","year":"2018","journal-title":"arXiv 1809 08895"},{"key":"ref11","author":"chung","year":"2018","journal-title":"Semi-supervised training for improving data efficiency in end-to-end speech synthesis"},{"key":"ref12","author":"graves","year":"2013","journal-title":"Generating Sequences with Recurrent Neural Networks"},{"key":"ref13","first-page":"2837","article-title":"Online and linear-time attention by enforcing monotonic alignments","volume":"70","author":"raffel","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref14","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":"ref15","author":"krueger","year":"2016","journal-title":"Zoneout Regularizing RNNs by Randomly Preserving Hidden Activations"},{"key":"ref16","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","author":"valin","year":"2018","journal-title":"LPCNET Improving neural speech synthesis through linear prediction"},{"key":"ref18","author":"chen","year":"2016","journal-title":"Guided Alignment Training for Topic-Aware Neural Machine Translation"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461829"},{"key":"ref4","author":"skerry-ryan","year":"2018","journal-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref6","author":"arik","year":"2017","journal-title":"Deep Voice Real-time neural text-to-speech"},{"key":"ref5","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","article-title":"Char2Wav: End-to-end speech synthesis","author":"sotelo","year":"2017","journal-title":"Proceedings of ICLR workshop submission"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511816338"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639215"},{"key":"ref9","article-title":"Deep Voice 3: 2000-speaker neural text-to-speech","author":"ping","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref20","first-page":"1","article-title":"Acoustic Modeling in Statistical Parametric Speech Synthesis–From HMM to LSTM-RNN","author":"zen","year":"2015","journal-title":"Proc MLSLP"},{"key":"ref22","author":"bahdanau","year":"2015","journal-title":"Neural machine translation by jointly learning to align and translate"},{"key":"ref21","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08703406.pdf?arnumber=8703406","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:54:33Z","timestamp":1641988473000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8703406\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2914149","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}