{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:37:18Z","timestamp":1730230638021,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413604","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"5719-5723","source":"Crossref","is-referenced-by-count":5,"title":["Prosodic Clustering for Phoneme-Level Prosody Control in End-to-End Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Alexandra","family":"Vioni","sequence":"first","affiliation":[]},{"given":"Myrsini","family":"Christidou","sequence":"additional","affiliation":[]},{"given":"Nikolaos","family":"Ellinas","sequence":"additional","affiliation":[]},{"given":"Georgios","family":"Vamvoukakis","sequence":"additional","affiliation":[]},{"given":"Panos","family":"Kakoulidis","sequence":"additional","affiliation":[]},{"given":"Taehoon","family":"Kim","sequence":"additional","affiliation":[]},{"given":"June Sig","family":"Sung","sequence":"additional","affiliation":[]},{"given":"Hyoungmin","family":"Park","sequence":"additional","affiliation":[]},{"given":"Aimilios","family":"Chalamandaris","sequence":"additional","affiliation":[]},{"given":"Pirros","family":"Tsiakoulis","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053436"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-49"},{"article-title":"Prosody transfer in neural text to speech using global pitch and loudness features","year":"2019","author":"gururani","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2861"},{"key":"ref14","first-page":"3331","article-title":"CHiVE: Varying prosody in speech synthesis with a linguistically driven dynamic hierarchical conditional variational network","author":"wan","year":"2019","journal-title":"Proc ICML"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683827"},{"key":"ref16","article-title":"Semi-supervised generative modeling for controllable speech synthesis","author":"habib","year":"2020","journal-title":"Proc ICLR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2571"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2464"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054106"},{"key":"ref28","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref4","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"Proc ICML"},{"key":"ref27","first-page":"219","article-title":"Modified k-means for better initial cluster centres","volume":"2","author":"joshi","year":"2013","journal-title":"International Journal of Computer Science and Mobile Computing"},{"key":"ref3","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","author":"skerry-ryan","year":"2018","journal-title":"Proc ICML"},{"article-title":"Effective use of variational embedding capacity in expressive end-to-end speech synthesis","year":"2019","author":"battenberg","key":"ref6"},{"key":"ref29","article-title":"Zoneout: Regularizing rnns by randomly preserving hidden activations","author":"krueger","year":"2017","journal-title":"Proc ICLR"},{"key":"ref5","article-title":"Hierarchical generative modeling for controllable speech synthesis","author":"hsu","year":"2018","journal-title":"Proc ICLR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053520"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref20","article-title":"Expressive speech synthesis for story-telling: the innoetics entry to the blizzard challenge 2016","author":"raptis","year":"2016","journal-title":"Proc Blizzard Challenge"},{"key":"ref22","first-page":"97","article-title":"Accurate short-term analysis of the fundamental frequency and the harmonics-to-noise ratio of a sampled sound","volume":"17","author":"boersma","year":"1993","journal-title":"Proceedings of the Institute of Phonetic Sciences"},{"key":"ref21","first-page":"12","article-title":"The htk book","volume":"3","author":"young","year":"2002","journal-title":"Cambridge University Engineering Department"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2041"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"article-title":"Melnet: A generative model for audio in the frequency domain","year":"2019","author":"vasquez","key":"ref26"},{"article-title":"Generating sequences with recurrent neural networks","year":"2013","author":"graves","key":"ref25"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413604.pdf?arnumber=9413604","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:53Z","timestamp":1652197253000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413604\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413604","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}