{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T15:22:27Z","timestamp":1772205747333,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746253","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"7587-7591","source":"Crossref","is-referenced-by-count":12,"title":["Hierarchical Prosody Modeling and Control in Non-Autoregressive Parallel Neural TTS"],"prefix":"10.1109","author":[{"given":"Tuomo","family":"Raitio","sequence":"first","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangchuan","family":"Li","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shreyas","family":"Seshadri","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2020-192"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682353"},{"key":"ref10","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"ICML"},{"key":"ref11","article-title":"Hierarchical generative modeling for controllable speech synthesis","author":"hsu","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053520"},{"key":"ref14","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with Tacotron","author":"skerry-ryan","year":"2018","journal-title":"ICML"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-49"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2861"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-628"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-17"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2015.10.007"},{"key":"ref28","article-title":"Audio samples from Hierarchical prosody modeling and control in non-autoregressive parallel neural TTS","year":"2021"},{"key":"ref4","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"SSW9"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1798"},{"key":"ref3","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020"},{"key":"ref6","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"NeurIPS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-46"},{"key":"ref5","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018"},{"key":"ref8","article-title":"End-to-end adversarial text-to-speech","author":"donahue","year":"2021","journal-title":"ICLRE"},{"key":"ref7","article-title":"Parallel Tacotron: Non-autoregressive and controllable TTS","author":"elias","year":"2020"},{"key":"ref2","article-title":"Deep Voice 3: 2000-speaker neural text-to-speech","author":"ping","year":"2018","journal-title":"ICLRE"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383629"},{"key":"ref1","article-title":"Natural TTS synthesis by conditioning WaveNet on Mel spectrogram predictions","author":"shen","year":"2017","journal-title":"ICASSP"},{"key":"ref20","article-title":"CHiVE: Varying prosody in speech synthesis with a linguistically driven dynamic hierarchical conditional variational network","author":"wan","year":"2019","journal-title":"ICML"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1446"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383591"},{"key":"ref24","first-page":"2417","article-title":"Voice quality: The 4th prosodic dimension","author":"campbell","year":"2003","journal-title":"Proc 15th ICPhS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-471"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688154"},{"key":"ref25","article-title":"Attention is all you need","author":"vaswani","year":"2017"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746253.pdf?arnumber=9746253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T16:11:58Z","timestamp":1661184718000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746253\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746253","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}