{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T08:42:45Z","timestamp":1774946565070,"version":"3.50.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"name":"AI Singapore Programme"},{"name":"National Robotics Programme","award":["192 25 00054"],"award-info":[{"award-number":["192 25 00054"]}]},{"name":"Advanced Manufacturing and Engineering Programmatic","award":["A1687b0033"],"award-info":[{"award-number":["A1687b0033"]}]},{"name":"Advanced Manufacturing and Engineering Programmatic","award":["A18A2b0046"],"award-info":[{"award-number":["A18A2b0046"]}]},{"name":"SUTD Start-up Grant Artificial Intelligence for Human Voice Conversion"},{"name":"SUTD AI Grant"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61773224"],"award-info":[{"award-number":["61773224"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/lsp.2020.3016564","type":"journal-article","created":{"date-parts":[[2020,8,13]],"date-time":"2020-08-13T20:19:11Z","timestamp":1597349951000},"page":"1470-1474","source":"Crossref","is-referenced-by-count":17,"title":["Modeling Prosodic Phrasing With Multi-Task Learning in Tacotron-Based TTS"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4524-7413","authenticated-orcid":false,"given":"Rui","family":"Liu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8078-3305","authenticated-orcid":false,"given":"Berrak","family":"Sisman","sequence":"additional","affiliation":[]},{"given":"Feilong","family":"Bao","sequence":"additional","affiliation":[]},{"given":"Guanglai","family":"Gao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9158-9401","authenticated-orcid":false,"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"94","article-title":"TH-CoSS, a Mandarin speech corpus for TTS","volume":"21","author":"cai","year":"2007","journal-title":"J Chin Inf Process"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50012-5"},{"key":"ref33","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":"ref32","article-title":"Feature reinforcement with word embedding and parsing information in neural TTS","author":"ming","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2167"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682368"},{"key":"ref37","first-page":"6699","article-title":"Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and auto-regressive prosody prior","author":"sun","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682353"},{"key":"ref35","first-page":"94","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":"ref34","first-page":"595","article-title":"Predicting expressive speaking style from text in end-to-end speech synthesis","author":"stanton","year":"0","journal-title":"Proc IEEE Spoken Lang Technol Workshop"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1311"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706263"},{"key":"ref11","first-page":"712","article-title":"An investigation of multi-speaker training for WaveNet vocoder","author":"hayashi","year":"0","journal-title":"Proc IEEE Autom Speech Recognit Understanding Workshop"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1288"},{"key":"ref13","first-page":"1978","article-title":"A voice conversion framework with tandem feature sparse representation and speakera-adapted WaveNet vocoder","author":"sisman","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2910637"},{"key":"ref15","first-page":"282","article-title":"Adaptive wavenet vocoder for residual compensation in GAN-based voice conversion","author":"sisman","year":"0","journal-title":"Proc IEEE Spoken Lang Technol Workshop"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref17","first-page":"3274","article-title":"Speech enhancement and recognition using multi-task learning of long short-term memory recurrent neural networks","author":"chen","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref19","first-page":"854","article-title":"Fusion of multiple parameterisations for DNN-based sinusoidal speech synthesis with multi-task learning","author":"hu","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178906"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0041"},{"key":"ref3","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":"ref6","first-page":"6274","article-title":"Teacher-student training for robust tacotron-based TTS","author":"liu","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref29","first-page":"269","article-title":"Prosody prediction from syntactic, lexical, and word embedding features","author":"sloan","year":"0","journal-title":"Proc ISCA Speech Synthesis Workshop"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683862"},{"key":"ref7","first-page":"245","article-title":"WaveTTS: Tacotron-based TTS with joint time-frequency domain loss","author":"liu","year":"0","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref2","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":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1972"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref20","first-page":"685","article-title":"Statistical parametric speech synthesis using generative adversarial networks under a multi-task learning framework","author":"yang","year":"0","journal-title":"Proc IEEE Autom Speech Recognit Understanding Workshop"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2467"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178814"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1706"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1159"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2028"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1113"},{"key":"ref26","first-page":"214","article-title":"Acoustic differentiation of L- and L-L% in switchboard and radio news speech","author":"kim","year":"0","journal-title":"Proc Speech Prosody"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1121\/1.402450"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/8966529\/09166626.pdf?arnumber=9166626","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,25]],"date-time":"2022-01-25T20:59:15Z","timestamp":1643144355000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9166626\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/lsp.2020.3016564","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}