{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T12:42:13Z","timestamp":1766580133452},"reference-count":32,"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\/icassp39728.2021.9414413","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6578-6582","source":"Crossref","is-referenced-by-count":12,"title":["Camp: A Two-Stage Approach to Modelling Prosody in Context"],"prefix":"10.1109","author":[{"given":"Zack","family":"Hodari","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexis","family":"Moinet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sri","family":"Karlapati","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaime","family":"Lorenzo-Trueba","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Merritt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arnaud","family":"Joly","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ammar","family":"Abbas","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":[{"article-title":"Towards transfer learning for end-to-end speech synthesis from deep pre-trained language models","year":"2019","author":"fang","key":"ref32"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3177"},{"key":"ref30","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"},{"key":"ref10","first-page":"6306","article-title":"Neural discrete representation learning","author":"den oord","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2904"},{"article-title":"Hierarchical representation of prosody for statistical speech synthesis","year":"2015","author":"suni","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2571"},{"key":"ref15","first-page":"4909","article-title":"A multi-level representation of F0 using the continuous wavelet transform and the discrete cosine transform","author":"ribeiro","year":"2015","journal-title":"Proc ICASSP"},{"article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","year":"2018","author":"wang","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1411"},{"key":"ref18","first-page":"157","article-title":"A vector quantized variational autoencoder (VQ-VAE) autoregressive neural F0 model for statistical parametric speech synthesis","author":"wang","year":"2019","journal-title":"IEEE TASLP"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2020-197"},{"key":"ref28","first-page":"3918","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","author":"oord","year":"2018","journal-title":"Proc ICML"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1174"},{"key":"ref27","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc NAACL-HLT"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-43"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511808814"},{"article-title":"Method for the subjective assessment of intermediate quality level of audio systems","year":"2014","author":"series","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-18"},{"key":"ref8","first-page":"311","article-title":"Toward a bestiary of English intonational contours","author":"goodhue","year":"2016","journal-title":"Proc NELS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1017\/9781316848265"},{"article-title":"Prosody generation for text-to-speech synthesis","year":"2019","author":"ronanki","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2530"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1251"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639682"},{"article-title":"DurIAN: Duration informed attention network for multimodal synthesis","year":"2019","author":"yu","key":"ref24"},{"article-title":"FastSpeech 2: Fast and high-quality end-to-end text-to-speech","year":"2020","author":"ren","key":"ref23"},{"key":"ref26","first-page":"238","article-title":"Learning with lookahead: Can history-based models rival globally optimized models?","author":"tsuruoka","year":"2011","journal-title":"Proc Computational Natural Language Learning"},{"key":"ref25","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"}],"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\/09414413.pdf?arnumber=9414413","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T08:30:36Z","timestamp":1672129836000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414413\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414413","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}