{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:51:18Z","timestamp":1783612278493,"version":"3.55.0"},"reference-count":101,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"SUTD Start-up Grant Artificial Intelligence for Human Voice Conversion","award":["2020 158"],"award-info":[{"award-number":["2020 158"]}]},{"name":"The Understanding and Synthesis of Expressive Speech by AI"},{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","award":["AISG-GC-2019-002"],"award-info":[{"award-number":["AISG-GC-2019-002"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","award":["AISG-100E-2018-006"],"award-info":[{"award-number":["AISG-100E-2018-006"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Robotics Programme","award":["1922500054"],"award-info":[{"award-number":["1922500054"]}]},{"name":"RIE2020 Advanced Manufacturing and Engineering Programmatic","award":["A1687b0033"],"award-info":[{"award-number":["A1687b0033"]}]},{"name":"RIE2020 Advanced Manufacturing and Engineering Programmatic","award":["A18A2b0046"],"award-info":[{"award-number":["A18A2b0046"]}]}],"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.2021.3076369","type":"journal-article","created":{"date-parts":[[2021,4,30]],"date-time":"2021-04-30T19:56:27Z","timestamp":1619812587000},"page":"1806-1818","source":"Crossref","is-referenced-by-count":50,"title":["Expressive TTS Training With Frame and Style Reconstruction Loss"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4524-7413","authenticated-orcid":false,"given":"Rui","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8078-3305","authenticated-orcid":false,"given":"Berrak","family":"Sisman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanglai","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9158-9401","authenticated-orcid":false,"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.168"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"ref33","first-page":"4693","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 PMLR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639682"},{"key":"ref31","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0041"},{"key":"ref37","first-page":"658","article-title":"Generating images with perceptual similarity metrics based on deep networks","author":"dosovitskiy","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","article-title":"Seen and unseen emotional style transfer for voice conversion with a new emotional speech dataset","author":"zhou","year":"0"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053436"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053520"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2020-197"},{"key":"ref27","first-page":"4417","article-title":"Improved prosody from learned F0 codebook representations for VQ-VAE speech waveform reconstruction","author":"zhao","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref29","first-page":"867","article-title":"ToBI: A standard for labeling english prosody","author":"silverman","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref20","first-page":"1085","article-title":"Group sparse representation with WaveNet vocoder adaptation for spectrum and prosody conversion","volume":"27","author":"sisman","year":"2019","journal-title":"IEEE Transactions on Audio"},{"key":"ref22","first-page":"515","article-title":"Pragmatics and intonation","author":"hirschberg","year":"2004","journal-title":"The Handbook of Pragmatics"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639507"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953089"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3040523"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3_4"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-43"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282110"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023309"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682353"},{"key":"ref59","first-page":"2318","article-title":"Hierarchical modeling of F0 contours for voice conversion","author":"sanchez","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref58","first-page":"1732","article-title":"Text-independent F0 transformation with non-parallel data for voice conversion","author":"wu","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref57","first-page":"2274","article-title":"Multilevel parametric-base F0 model for speech synthesis","author":"latorre","year":"0","journal-title":"Proc Ann Conf Int Speech Commun Assoc INTERSPEECH"},{"key":"ref56","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":"ref55","doi-asserted-by":"publisher","DOI":"10.20396\/joss.v1i1.15014"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511808814"},{"key":"ref53","first-page":"153","author":"wennerstrom","year":"2001","journal-title":"The Music of Everyday Speech Prosody and Discourse Analysis"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178904"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052944"},{"key":"ref4","first-page":"4006","article-title":"Tacotron: A fully end-to-end text-to-speech synthesis model","author":"wang","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-8111-8_10"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-35"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00379"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref9","first-page":"227","article-title":"An HMM-based speech synthesis system applied to english","author":"tokuda","year":"0","journal-title":"Proc IEEE Workshop Speech Synth"},{"key":"ref46","first-page":"125","article-title":"Wavenet: A generative model for raw","author":"oord","year":"0","journal-title":"Proc 9th ISCA Speech Synthesis Workshop"},{"key":"ref45","first-page":"2410","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00804"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref41","first-page":"3","article-title":"Peaq-the itu standard for objective measurement of perceived audio quality","volume":"48","author":"thiede","year":"2000","journal-title":"J Audio Eng Soc"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref43","article-title":"The peass toolkit-perceptual evaluation methods for audio source separation","author":"emiya","year":"0","journal-title":"Proc 9th Int Conf on Latent Variable Analysis and Signal Separation"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1924"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054578"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053110"},{"key":"ref70","first-page":"3331","article-title":"Chive: Varying prosody in speech synthesis with a linguistically driven dynamic hierarchical conditional variational network","author":"kenter","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref76","first-page":"3918","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","volume":"80","author":"van den oord","year":"0","journal-title":"Proc 35th Int Conf Mach Learn ser Proc Mach Learn Res"},{"key":"ref77","first-page":"3974","article-title":"From speaker verification to multispeaker speech synthesis, deep transfer with feedback constraint","author":"cai","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.3390\/app10082884"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683077"},{"key":"ref79","first-page":"p. 1","article-title":"Auto-encoding variational bayes","volume":"1050","author":"kingma","year":"2014","journal-title":"Statist"},{"key":"ref60","first-page":"78","article-title":"Continuous wavelet transform for analysis of speech prosody","author":"vainio","year":"2013","journal-title":"Laboratoire Parole et Lang"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472664"},{"key":"ref61","first-page":"285","article-title":"Wavelets for intonation modeling in HMM speech synthesis","author":"suni","year":"0","journal-title":"Proc 8th ISCA Speech Synth Workshop"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-984"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-017-0116-2"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1053"},{"key":"ref66","first-page":"2461","article-title":"Modeling of various speaking styles and emotions for HMM-based speech synthesis","author":"yamagishi","year":"0","journal-title":"Proc 8th Eur Conf Speech Commun Technol"},{"key":"ref67","first-page":"1","article-title":"Hmm-based speech synthesis with various speaking styles using model interpolation","author":"tachibana","year":"0","journal-title":"Proc Speech Prosody Int Conf"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288797"},{"key":"ref2","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"0","journal-title":"Proc ICASSP IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953089"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref95","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref94","article-title":"The LJ speech dataset","author":"ito","year":"0"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2860246"},{"key":"ref91","first-page":"237","article-title":"Improved bottleneck features using pretrained deep neural networks","author":"yu","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref90","article-title":"Cambridge, MA, USA: MIT Press","author":"goodfellow","year":"2016"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/IALP.2017.8300542"},{"key":"ref99","first-page":"6365","article-title":"The investigation of frame disturbance (FD) in perceptual evaluation speech quality (PESQ) as a perceptual metric","volume":"10","author":"jusoh","year":"2015","journal-title":"ARPN J Eng Appl Sci"},{"key":"ref96","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.04.016"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683862"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1972"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1311"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054681"},{"key":"ref15","article-title":"Graphspeech: Syntax-aware graph attention network for neural speech synthesis","author":"liu","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269007"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2766843"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1528"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1568"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1288"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1121\/1.405558"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1131"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2898816"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfds.2017.05.001"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/S1071-5819(02)00141-6"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023186"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3069"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053732"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09420276.pdf?arnumber=9420276","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T20:00:23Z","timestamp":1639771223000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9420276\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":101,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3076369","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}