{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T13:07:42Z","timestamp":1725455262741},"reference-count":23,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/slt.2018.8639679","type":"proceedings-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T23:36:34Z","timestamp":1550187394000},"page":"332-338","source":"Crossref","is-referenced-by-count":0,"title":["Examplar-Based Speechwaveform Generation for Text-To-Speech"],"prefix":"10.1109","author":[{"given":"Cassia","family":"Valentini-Botinhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oliver","family":"Watts","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Felipe","family":"Espic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"King","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-398","article-title":"HMM-based unit selection using frame sized speech segments","author":"ling","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref11","article-title":"Utilization of an HMM-based feature generation module in 5 ms segment concatenative speech synthesis","author":"hirai","year":"2007","journal-title":"Proc of SSW6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947509"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2221460"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2016.7918404"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2045239"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1647","article-title":"Direct modelling of magnitude and phase spectra for statistical parametric speech synthesis","author":"espic","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref17","article-title":"The CSTR entry to the Blizzard Challenge 2017","author":"ronanki","year":"2017","journal-title":"Proc Blizzard Challenge Workshop"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.01.014"},{"key":"ref19","first-page":"147","article-title":"The architecture of the festival speech synthesis system","author":"taylor","year":"1998","journal-title":"Proc ESCA\/IEEE Workshop Speech Synthesis"},{"journal-title":"WaveNet A Generative Model for Raw Audio","year":"0","author":"van den oord","key":"ref4"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1107","article-title":"Google’s next-generation real-time unit-selection synthesizer using sequence-to-sequence LSTM-based autoencoders","author":"wan","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"journal-title":"Samplernn An unconditional end-to-end neural audio generation model","year":"0","author":"mehri","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1857"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1798","article-title":"Siri ondevice deep learning-guided unit selection text-to-speech system","author":"capes","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472658"},{"key":"ref9","article-title":"The CSTR entry to the 2018 Blizzard Challenge","author":"espic","year":"2018","journal-title":"Proc Blizzard Challenge Workshop"},{"year":"2017","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAU.1969.1162058"},{"key":"ref21","first-page":"218","article-title":"Merlin: An open source neural network speech synthesis system","author":"wu","year":"2016","journal-title":"Proc of SSW6"},{"journal-title":"Method for the Subjective Assessment of Intermediate Quality Level of Coding Systems","year":"2003","key":"ref23"}],"event":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2018,12,18]]},"location":"Athens, Greece","end":{"date-parts":[[2018,12,21]]}},"container-title":["2018 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8632666\/8639030\/08639679.pdf?arnumber=8639679","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T04:50:56Z","timestamp":1643259056000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8639679\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/slt.2018.8639679","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}