{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T23:06:56Z","timestamp":1777504016797,"version":"3.51.4"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/taslp.2022.3171974","type":"journal-article","created":{"date-parts":[[2022,5,3]],"date-time":"2022-05-03T20:15:18Z","timestamp":1651608918000},"page":"1789-1802","source":"Crossref","is-referenced-by-count":11,"title":["Decoding Knowledge Transfer for Neural Text-to-Speech Training"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4524-7413","authenticated-orcid":false,"given":"Rui","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Computer Science, Inner Mongolia University, Hohhot, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8078-3305","authenticated-orcid":false,"given":"Berrak","family":"Sisman","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design (SUTD), Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanglai","family":"Gao","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Inner Mongolia University, Hohhot, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9158-9401","authenticated-orcid":false,"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"School of Data Science, The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639215"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-33"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-8111-8_10"},{"key":"ref7","first-page":"125","article-title":"WaveNet: A generative model for raw audio","volume-title":"Proc. ISCA Speech Synth. Workshop","author":"Oord","year":"2016"},{"key":"ref8","first-page":"4700","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"80","author":"Skerry-Ryan","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-35"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-4115(97)80111-2"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269007"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1288"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/ssw.2019-38"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1824"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053546"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-286"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1972"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1706"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2325"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3040523"},{"key":"ref24","first-page":"1","article-title":"Sequence level training with recurrent neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ranzato","year":"2016"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5616"},{"key":"ref26","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bengio","year":"2015"},{"key":"ref27","article-title":"How (not) to train your generative model: Scheduled sampling, likelihood, adversary?","author":"Huszr","year":"2015"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3156\/jsoft.29.5_177_2"},{"key":"ref29","first-page":"4601","article-title":"Professor forcing: A new algorithm for training recurrent networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Goyal","year":"2016"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9590"},{"key":"ref31","first-page":"1","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. NIPS 2014 Deep Learn. Workshop","author":"Hinton","year":"2015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054681"},{"key":"ref33","first-page":"1106","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky","year":"2012"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"ref35","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_2"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018142"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240632"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1426"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1662"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2176"},{"key":"ref44","first-page":"1","article-title":"Adversarial training methods for semi-supervised text classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Miyato","year":"2017"},{"key":"ref45","first-page":"534","article-title":"Adversarial neural machine translation","volume-title":"Proc. Asian Conf. Mach. Learn.","volume":"95","author":"Wu","year":"2018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462581"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.5555\/2946645.2946704"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1139"},{"key":"ref49","first-page":"1602","article-title":"Born-again neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"80","author":"Furlanello","year":"2018"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3055564"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2582"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3071662"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.07.048"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449898"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682450"},{"key":"ref57","first-page":"2226","article-title":"Improved techniques for training GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Salimans","year":"2016"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-49430-8_3"},{"key":"ref59","first-page":"1","article-title":"The IMU speech synthesis entry for blizzard challenge 2019","volume-title":"Proc. Blizzard Challenge","volume":"2019","author":"Liu","year":"2019"},{"key":"ref60","first-page":"3165","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren","year":"2019"},{"key":"ref61","first-page":"7586","article-title":"Non-autoregressive neural text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"119","author":"Peng","year":"2020"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3_4"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076369"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1080\/00223890802107925"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107337855"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.4337\/9781781003152.00014"},{"key":"ref70","first-page":"1","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ping","year":"2018"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3016564"},{"key":"ref72","first-page":"5167","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"80","author":"Wang","year":"2018"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09767637.pdf?arnumber=9767637","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T22:43:43Z","timestamp":1705963423000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9767637\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3171974","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}