{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,13]],"date-time":"2025-09-13T16:20:23Z","timestamp":1757780423812},"reference-count":24,"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\/icassp39728.2021.9413696","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6573-6577","source":"Crossref","is-referenced-by-count":7,"title":["Prosodic Representation Learning and Contextual Sampling for Neural Text-to-Speech"],"prefix":"10.1109","author":[{"given":"Sri","family":"Karlapati","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ammar","family":"Abbas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zack","family":"Hodari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexis","family":"Moinet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arnaud","family":"Joly","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Penny","family":"Karanasou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Drugman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1113"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3177"},{"article-title":"Feature reinforcement with word embedding and parsing information in neural TTS","year":"2019","author":"ming","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2167"},{"article-title":"Dynamic prosody generation for speech synthesis using linguistics-driven acoustic embedding selection","year":"2019","author":"tyagi","key":"ref15"},{"key":"ref16","article-title":"BERT: Pretraining of Deep Bidirectional Transformers for Language Understanding","author":"devlin","year":"2019","journal-title":"NAACL-HLT (1)"},{"key":"ref17","article-title":"Graph Attention Networks","author":"veli?kovi?","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref18","article-title":"How to Train Deep Variational Autoencoders and Probabilistic Ladder Networks","author":"s\u00f8nderby","year":"2016","journal-title":"33rd International Conference on Machine Learning (ICML 2016) International Conference on Machine Learning"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1080\/01690961003589492"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"article-title":"Durian: Duration informed attention network for multimodal synthesis","year":"2019","author":"yu","key":"ref3"},{"key":"ref6","first-page":"2410","article-title":"Efficient Neural Audio Synthesis","author":"kalchbrenner","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref5","first-page":"125","article-title":"WaveNet: A Generative Model for Raw Audio","author":"den oord","year":"2016","journal-title":"9th ISCA Speech Synthesis Workshop"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref7","first-page":"4693","article-title":"Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron","author":"skerry-ryan","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards End-to-End Speech Synthesis","author":"wang","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1251"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1162\/tacl_a_00349","article-title":"A primer in bertology: What we know about how BERT works","author":"rogers","year":"2020"},{"article-title":"Gated graph sequence neural networks","year":"2015","author":"li","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2530"},{"year":"2003","key":"ref24","article-title":"1534-1, \"Method for the subjective assessment of intermediate quality levels of coding systems (MUSHRA)"},{"article-title":"Graph neural networks: A review of methods and applications","year":"2018","author":"zhou","key":"ref23"}],"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\/09413696.pdf?arnumber=9413696","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T08:29:41Z","timestamp":1672129781000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413696\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413696","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}