{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T16:10:26Z","timestamp":1782835826462,"version":"3.54.5"},"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\/icassp43922.2022.9746744","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7582-7586","source":"Crossref","is-referenced-by-count":7,"title":["Prosodyspeech: Towards Advanced Prosody Model for Neural Text-to-Speech"],"prefix":"10.1109","author":[{"given":"Yuanhao","family":"Yi","sequence":"first","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"He","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shifeng","family":"Pan","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujia","family":"Xiao","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref31","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref10","article-title":"Fastspeech 2: Fast and high-quality end-to-end text-to-speech","author":"ren","year":"2020"},{"key":"ref11","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":"International Conference on Machine Learning"},{"key":"ref12","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":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref14","article-title":"Hierarchical generative modeling for controllable speech synthesis","author":"hsu","year":"2018"},{"key":"ref15","article-title":"Effective use of variational embedding capacity in expressive end-to-end speech synthesis","author":"battenberg","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053520"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288797"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054556"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076369"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1722"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.3160360204"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2045237"},{"key":"ref6","first-page":"214","article-title":"Deep voice 3: 2000-speaker neural text-to-speech","author":"ping","year":"2018","journal-title":"Proc ICLR"},{"key":"ref29","article-title":"Improved training of wasserstein gans","author":"gulrajani","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref7","article-title":"Clarinet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854321"},{"key":"ref9","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE.2019.8661919"},{"key":"ref22","article-title":"Attention is all you need","author":"vaswani","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2096"},{"key":"ref24","article-title":"Adaspeech: Adaptive text to speech for custom voice","author":"chen","year":"2021"},{"key":"ref23","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref26","first-page":"531","article-title":"Mutual information neural estimation","author":"belghazi","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054591"}],"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\/09746744.pdf?arnumber=9746744","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:11:42Z","timestamp":1661199102000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746744\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746744","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}