{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T03:29:25Z","timestamp":1752550165112,"version":"3.37.3"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3313424","type":"journal-article","created":{"date-parts":[[2023,9,8]],"date-time":"2023-09-08T17:38:56Z","timestamp":1694194736000},"page":"3706-3716","source":"Crossref","is-referenced-by-count":4,"title":["Pronunciation Dictionary-Free Multilingual Speech Synthesis Using Learned Phonetic Representations"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1661-1113","authenticated-orcid":false,"given":"Chang","family":"Liu","sequence":"first","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7853-5273","authenticated-orcid":false,"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4247-4128","authenticated-orcid":false,"given":"Ling-Hui","family":"Chen","sequence":"additional","affiliation":[{"name":"iFLYTEK Research, iFLYTEK Company Ltd., Hefei, China"}]}],"member":"263","reference":[{"key":"ref13","first-page":"3171","article-title":"FastSpeech: Fast, robust and controllable text to speech","author":"ren","year":"0","journal-title":"Proc 33rd Int Conf Neural Inf Process Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref14","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref11","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1017\/9781108783071"},{"key":"ref17","first-page":"6309","article-title":"Neural discrete representation learning","author":"oord","year":"0","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref16","first-page":"223","article-title":"A comparison between letters and phones as input to sequence-to-sequence models for speech synthesis","author":"fong","year":"0","journal-title":"Proc 10th ISCA Speech Synth Workshop"},{"key":"ref19","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"oord","key":"ref18"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461829"},{"key":"ref45","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"0","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"article-title":"The LJ speech dataset","year":"2017","author":"ito","key":"ref47"},{"key":"ref42","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"0","journal-title":"Proc 34th Int Conf Neural Inf Process Syst"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.68"},{"key":"ref44","first-page":"10524","article-title":"On layer normalization in the transformer architecture","author":"xiong","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.1017\/9780511807954","author":"association","year":"1999","journal-title":"Handbook of the International Phonetic Association A Guide to the Use of the International Phonetic Alphabet"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref8","article-title":"Epitran: Precision G2P for many languages","author":"mortensen","year":"0","journal-title":"Proc 11th Int Conf Lang Resour Eval"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03958"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-538"},{"article-title":"A survey on neural speech synthesis","year":"2021","author":"tan","key":"ref4"},{"journal-title":"Human Computer Interaction","year":"2005","author":"kumar","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1038"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462678"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1504"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095776"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2892235"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683746"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1043"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-91"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746858"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053094"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511816338"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10140"},{"key":"ref39","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"0","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Human Lang Technol"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413566"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415079"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-489"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10797"},{"key":"ref20","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref22","first-page":"27826","article-title":"Unsupervised speech recognition","author":"baevski","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref28","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367023"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10244053.pdf?arnumber=10244053","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,21]],"date-time":"2023-12-21T11:55:08Z","timestamp":1703159708000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10244053\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3313424","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2023]]}}}