{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T04:48:35Z","timestamp":1747284515468},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053546","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"6724-6728","source":"Crossref","is-referenced-by-count":4,"title":["Effect of Choice of Probability Distribution, Randomness, and Search Methods for Alignment Modeling in Sequence-to-Sequence Text-to-Speech Synthesis Using Hard Alignment"],"prefix":"10.1109","author":[{"given":"Yusuke","family":"Yasuda","sequence":"first","affiliation":[]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-20"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/0022-2496(77)90026-8"},{"article-title":"The concrete distribution: A continuous relaxation of discrete random variables","year":"0","author":"maddison","key":"ref12"},{"article-title":"Categorical reparameterization with gumbel-softmax","year":"0","author":"jang","key":"ref13"},{"key":"ref14","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":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1227"},{"key":"ref16","article-title":"Zoneout: Regularizing rnns by randomly preserving hidden activations","author":"krueger","year":"2017","journal-title":"Proc ICLR"},{"key":"ref17","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proc ICLR"},{"key":"ref18","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref3","article-title":"Deep Voice 3: Scaling text-to-speech with convolutional sequence learning","author":"ping","year":"2018","journal-title":"Proc ICLR"},{"key":"ref6","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"CoRR"},{"key":"ref5","article-title":"Close to human quality TTS with transformer","author":"li","year":"2018","journal-title":"CoRR"},{"key":"ref8","first-page":"211","article-title":"Initial investigation of encoder-decoder end-to-end TTS framework using marginalization of monotonic hard alignments","author":"yasuda","year":"0"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1972"},{"key":"ref2","article-title":"Char2wav: End-to-end speech synthesis","author":"sotelo","year":"2017","journal-title":"ICLR (workshop track)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1138"},{"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"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053546.pdf?arnumber=9053546","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:07:50Z","timestamp":1656374870000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053546\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053546","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}