{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T14:48:04Z","timestamp":1773326884656,"version":"3.50.1"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100013290","name":"National Key Research and Development Program of China Stem Cell and Translational Research","doi-asserted-by":"publisher","award":["2019YFF0303001"],"award-info":[{"award-number":["2019YFF0303001"]}],"id":[{"id":"10.13039\/501100013290","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61871358"],"award-info":[{"award-number":["61871358"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3074757","type":"journal-article","created":{"date-parts":[[2021,4,22]],"date-time":"2021-04-22T02:18:30Z","timestamp":1619057910000},"page":"1582-1593","source":"Crossref","is-referenced-by-count":17,"title":["Extracting and Predicting Word-Level Style Variations for Speech Synthesis"],"prefix":"10.1109","volume":"29","author":[{"given":"Ya-Jie","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7853-5273","authenticated-orcid":false,"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"The blizzard challenge 2019","volume":"2019","author":"wu","year":"0","journal-title":"Proc Blizzard Challenge Workshop"},{"key":"ref38","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Human Lang Technol"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1111\/j.1551-6709.2008.01007.x"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053436"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639682"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2571"},{"key":"ref37","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1037\/0096-1523.14.1.113"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/BF01708572"},{"key":"ref34","first-page":"63","article-title":"Prosody and the structure of the message","author":"cutler","year":"0","journal-title":"Proc Comput Prosody Comput Models Process Spontaneous Speech"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32381-3_16"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref61","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"0","journal-title":"Proc 12th USENIX Conf Operating Syst Des Implementation (OSDI) ser OSDI’16 USA USENIX Assoc"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1177\/001316446002000104"},{"key":"ref28","article-title":"Auto-encoding variational bayes","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref27","first-page":"4700","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","author":"skerry-ryan","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1894-4_22"},{"key":"ref20","first-page":"2415","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"0","journal-title":"Proc Int Conf Mach"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461332"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref24","first-page":"5167","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref23","first-page":"470","article-title":"Improved parallel WaveGAN vocoder with perceptually weighted spectrogram loss","author":"song","year":"0","journal-title":"Proc IEEE Spoken Lang Technol Workshop (SLT)"},{"key":"ref26","article-title":"Hierarchical generative modeling for controllable speech synthesis","author":"hsu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref50","first-page":"474","article-title":"Increasing prosodic variability of text-to-speech synthesizers","author":"n\u00e9meth","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhl174"},{"key":"ref59","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054337"},{"key":"ref55","article-title":"The USTC system for blizzard challenge 2019","author":"jiang","year":"0","journal-title":"Proc Blizzard Challenge Workshop"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1418"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010438900737"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1515\/9783110261790.119"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref11","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","author":"ping","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3177"},{"key":"ref12","first-page":"4006","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref13","article-title":"Char2wav: End-to-end speech synthesis","author":"sotelo","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref14","first-page":"3165","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2968"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054484"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2123"},{"key":"ref18","article-title":"WaveNet: A generative model for raw audio","author":"van denoord","year":"0","journal-title":"Proc 9th ISCA Speech Synth Workshop"},{"key":"ref19","article-title":"Clarinet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"601","DOI":"10.21437\/Eurospeech.1997-219","article-title":"Automatically clustering similar units for unit selection in speech synthesis","author":"black","year":"1997","journal-title":"Proc Eur Conf Speech Commun Technol"},{"key":"ref3","first-page":"391","article-title":"A corpus-based chinese speech synthesis with contextual dependent unit selection","author":"wang","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367298"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"ref8","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-45258-5_13"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref46","first-page":"2318","article-title":"Hierarchical modeling of F0 contours for voice conversion","author":"sanchez","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.20396\/joss.v1i1.15014"},{"key":"ref48","first-page":"2170","article-title":"A hierarchical F0 modeling method for HMM-based speech synthesis","author":"lei","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CHINSL.2008.ECP.44"},{"key":"ref42","article-title":"Text-independent F0 transformation with non-parallel data for voice conversion","author":"wu","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref41","article-title":"Expressive TTS training with frame and style reconstruction loss","author":"liu","year":"2020"},{"key":"ref44","first-page":"1537","article-title":"Transformation of prosody in voice conversion","author":"?i?man","year":"0","journal-title":"Proc Asia-Pacific Signal Inf Process Assoc Annu Summit Conf"},{"key":"ref43","first-page":"2274","article-title":"Multilevel parametric-base F0 model for speech synthesis","author":"latorre","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09410373.pdf?arnumber=9410373","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,25]],"date-time":"2022-12-25T03:35:07Z","timestamp":1671939307000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9410373\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3074757","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}