{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T08:15:52Z","timestamp":1729671352641,"version":"3.28.0"},"reference-count":17,"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\/icassp40776.2020.9053812","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7659-7663","source":"Crossref","is-referenced-by-count":5,"title":["Extracting Unit Embeddings Using Sequence-To-Sequence Acoustic Models for Unit Selection Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Xiao","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"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":"ref10","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end- to-end speech synthesis","author":"wang","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"article-title":"Neural machine translation by jointly learning to align and translate","year":"2014","author":"bahdanau","key":"ref12"},{"key":"ref13","article-title":"The USTC system for Blizzard Challenge 2008","author":"ling","year":"2008","journal-title":"Blizzard Challenge Workshop"},{"key":"ref14","article-title":"The IFLYTEK System for Blizzard Challenge 2017","author":"liu","year":"2017","journal-title":"Blizzard Challenge Workshop"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-018-1336-0"},{"key":"ref16","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1978.1163055"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"581","DOI":"10.21437\/Eurospeech.1995-148","article-title":"Optimising selection of units from speech databases for concatenative synthesis","author":"black","year":"1995","journal-title":"Eurospeech"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-428"},{"key":"ref5","article-title":"Preselection of candidate units in a unit selection- based text-to-speech synthesis system","author":"conkie","year":"2000","journal-title":"Sixth International Conference on Spoken Language Processing"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00810-9_3"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1107"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1016\/j.specom.2009.04.004","article-title":"Statistical parametric speech synthesis","volume":"51","author":"zen","year":"2009","journal-title":"Speech Communication"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1109\/ICASSP.1996.541110","article-title":"Unit selection in a concatenative speech synthesis system using a large speech database","volume":"1","author":"hunt","year":"1996","journal-title":"Acoustics Speech and Signal Processing 1996 ICASSP-96 Conference Proceedings 1996 IEEE International Conference on"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1198"}],"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\/09053812.pdf?arnumber=9053812","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T19:28:57Z","timestamp":1696015737000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053812\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053812","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}