{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T12:28:31Z","timestamp":1775737711172,"version":"3.50.1"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682353","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"6905-6909","source":"Crossref","is-referenced-by-count":46,"title":["Investigation of Enhanced Tacotron Text-to-speech Synthesis Systems with Self-attention for Pitch Accent Language"],"prefix":"10.1109","author":[{"given":"Yusuke","family":"Yasuda","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Takaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Zoneout: Regularizing rnns by randomly preserving hidden activations","author":"krueger","year":"2017","journal-title":"Proc ICLR"},{"key":"ref11","article-title":"A structured self-attentive sentence embedding","author":"lin","year":"2017","journal-title":"Proc ICLR"},{"key":"ref12","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1004"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2828650"},{"key":"ref15","first-page":"2688","article-title":"Ximera: A concatenative speech synthesis system with large scale corpora","author":"kawai","year":"2006","journal-title":"IECE Transactions on Information and Systems (Japanese Edition)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1227"},{"key":"ref17","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proc ICLR"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"240","DOI":"10.21437\/Odyssey.2018-34","article-title":"Can we steal your vocal identity from the internetƒ: Initial investigation of cloning obamas voice using gan, wavenet and low-quality found data","author":"lorenzo-trueba","year":"2018","journal-title":"Proc Odyssey 2018 The Speaker and Language Recognition Workshop"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461452"},{"key":"ref4","article-title":"Clarinet: Parallel wave generation in end-to-end text-to-speech","volume":"abs 1807 7281","author":"ping","year":"2018","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1381"},{"key":"ref5","article-title":"Close to human quality TTS with transformer","volume":"abs 1809 8895","author":"li","year":"2018","journal-title":"CoRR"},{"key":"ref8","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc ICLR"},{"key":"ref7","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc NIPS"},{"key":"ref2","article-title":"Wavenet: A generative model for raw audio","volume":"abs 1609 3499","author":"van den oord","year":"2016","journal-title":"CoRR"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462020"},{"key":"ref20","author":"wang","year":"2018","journal-title":"Fundamental Frequency Modeling for Neural-Network-Based Statistical Parametric Speech Synthesis"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, United Kingdom","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682353.pdf?arnumber=8682353","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,14]],"date-time":"2022-07-14T23:12:51Z","timestamp":1657840371000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682353\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682353","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}