{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T13:54:51Z","timestamp":1771336491448,"version":"3.50.1"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,25]],"date-time":"2022-10-25T00:00:00Z","timestamp":1666656000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,25]],"date-time":"2022-10-25T00:00:00Z","timestamp":1666656000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,25]]},"DOI":"10.1109\/icspcc55723.2022.9984283","type":"proceedings-article","created":{"date-parts":[[2022,12,23]],"date-time":"2022-12-23T18:42:22Z","timestamp":1671820942000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["A Comparison of Text Selection Algorithms for Sequence-to-Sequence Neural TTS"],"prefix":"10.1109","author":[{"given":"Stefan","family":"Taubert","sequence":"first","affiliation":[{"name":"Chemnitz University of Technology,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jasmin","family":"Sternkopf","sequence":"additional","affiliation":[{"name":"Chemnitz University of Technology,Department of Mathematics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Kahl","sequence":"additional","affiliation":[{"name":"Chemnitz University of Technology,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maximilian","family":"Eibl","sequence":"additional","affiliation":[{"name":"Chemnitz University of Technology,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"199","article-title":"An automated procedure for minimum size phonetically balanced phrases selection","volume":"2","author":"Falaschi","year":"1989","journal-title":"SIOA-1989"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1997-207"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362403"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-39"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref8","article-title":"FastSpeech: Fast, Robust and Controllable Text to Speech","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Ren","year":"2019"},{"key":"ref9","article-title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","volume-title":"International Conference on Learning Representations","author":"Ren"},{"key":"ref10","article-title":"The LJ Speech Dataset","author":"Ito","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2003-118"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2190"},{"key":"ref14","article-title":"The IRISA Text-To-Speech System for the Blizzard Challenge 2016","volume-title":"Blizzard Challenge 2016 workshop","author":"Alain"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2400"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2816"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-465"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-38"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1999-255"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2020-195"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-596"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2001-255"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-397"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854375"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/BF02579324"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-74"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683862"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403331"},{"key":"ref29","article-title":"Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis","author":"Valle","year":"2020"},{"key":"ref30","article-title":"Epitran: Precision G2P for Many Languages","volume-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)","author":"Mortensen"},{"key":"ref31","article-title":"Flite","author":"Black","year":"2017"},{"key":"ref32","article-title":"Effective Use of Variational Embedding Capacity in Expressive End-to-End Speech Synthesis","author":"Battenberg","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054556"},{"key":"ref34","article-title":"Tacotron 2 - PyTorch implementation with faster-than-realtime inference","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3"},{"key":"ref39","article-title":"Method for the subjective assessment of intermediate quality level of audio systems","year":"2015"}],"event":{"name":"2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","location":"Xi'an, China","start":{"date-parts":[[2022,10,25]]},"end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9984156\/9984215\/09984283.pdf?arnumber=9984283","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T05:36:10Z","timestamp":1706765770000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9984283\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,25]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icspcc55723.2022.9984283","relation":{},"subject":[],"published":{"date-parts":[[2022,10,25]]}}}