{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T21:35:16Z","timestamp":1776116116460,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"publisher","award":["T2EDK04248"],"award-info":[{"award-number":["T2EDK04248"]}],"id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000780","name":"European Union","doi-asserted-by":"publisher","award":["T2EDK04248"],"award-info":[{"award-number":["T2EDK04248"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10023268","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"977-983","source":"Crossref","is-referenced-by-count":4,"title":["Regotron: Regularizing the Tacotron2 Architecture Via Monotonic Alignment Loss"],"prefix":"10.1109","author":[{"given":"Efthymios","family":"Georgiou","sequence":"first","affiliation":[{"name":"Institute for Language and Speech Processing,Athena Research Center,Athens,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kosmas","family":"Kritsis","sequence":"additional","affiliation":[{"name":"Institute for Language and Speech Processing,Athena Research Center,Athens,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georgios","family":"Paraskevopoulos","sequence":"additional","affiliation":[{"name":"Institute for Language and Speech Processing,Athena Research Center,Athens,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Athanasios","family":"Katsamanis","sequence":"additional","affiliation":[{"name":"Institute for Language and Speech Processing,Athena Research Center,Athens,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vassilis","family":"Katsouros","sequence":"additional","affiliation":[{"name":"Institute for Language and Speech Processing,Athena Research Center,Athens,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandros","family":"Potamianos","sequence":"additional","affiliation":[{"name":"School of ECE, National Technical University of Athens,Athens,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"van den Oord","year":"2016","journal-title":"Wavenet: A generative model for raw audio"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref4","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","volume-title":"6th International Conference on Learning Representations, ICLR 2018","author":"Ping"},{"key":"ref5","first-page":"3918","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"van den Oord"},{"key":"ref6","first-page":"2415","article-title":"Efficient neural audio synthe-sis","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018","author":"Kalchbrenner","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref8","article-title":"End-to-end adver-sarial text-to-speech","volume-title":"9th International Conference on Learning Representations, ICLR","author":"Donahue"},{"key":"ref9","article-title":"Sequence to sequence learning with neural networks","volume":"27","author":"Sutskever","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"Clarinet: Parallel wave generation in end-to-end text-to-speech","volume-title":"7th International Conference on Learning Representations, ICLR","author":"Ping"},{"key":"ref11","article-title":"Neural speechsynthesis with transformer net-work","volume-title":"The Thirty-Third AAAI Conference on Artificial Intelligence","author":"Li"},{"key":"ref12","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"Ren","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref14","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Ren","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1461"},{"key":"ref16","article-title":"Flowtron: an autoregressive flow-based generative network for text-to-speech synthesis","volume-title":"9th International Conference on Learning Representations, ICLR","author":"Valle"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053915"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-831"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054484"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1405"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054106"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.31390\/gradschool_dissertations.4601"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-35"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461829"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2520"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-851"},{"key":"ref27","article-title":"Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search","author":"Kim","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054119"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9747707"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.354"},{"key":"ref31","article-title":"Attention-based models for speech recognition","volume":"28","author":"Chorowski","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","volume-title":"The lj speech dataset","author":"Ito","year":"2017"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","location":"Doha, Qatar","start":{"date-parts":[[2023,1,9]]},"end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10023268.pdf?arnumber=10023268","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T06:49:51Z","timestamp":1707806991000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10023268\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10023268","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}