{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T00:43:15Z","timestamp":1775090595057,"version":"3.50.1"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100020771","name":"Natural Science Foundation for Young Scientists of Shanxi Province","doi-asserted-by":"publisher","award":["62206136"],"award-info":[{"award-number":["62206136"]}],"id":[{"id":"10.13039\/501100020771","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Provincial Key Laboratory of Human Digital Twin","award":["2022B1212010004"],"award-info":[{"award-number":["2022B1212010004"]}]},{"name":"One Zone, Two Bases"},{"DOI":"10.13039\/501100003850","name":"Inner Mongolia University","doi-asserted-by":"publisher","award":["21300-231510"],"award-info":[{"award-number":["21300-231510"]}],"id":[{"id":"10.13039\/501100003850","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":[[2024]]},"DOI":"10.1109\/taslp.2023.3348762","type":"journal-article","created":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T19:50:33Z","timestamp":1704138633000},"page":"1075-1087","source":"Crossref","is-referenced-by-count":30,"title":["Text-to-Speech for Low-Resource Agglutinative Language With Morphology-Aware Language Model Pre-Training"],"prefix":"10.1109","volume":"32","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"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2276-1456","authenticated-orcid":false,"given":"Yifan","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Inner Mongolia University, Hohhot, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1412-2883","authenticated-orcid":false,"given":"Haolin","family":"Zuo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Inner Mongolia University, Hohhot, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4173-6319","authenticated-orcid":false,"given":"Zhaojie","family":"Luo","sequence":"additional","affiliation":[{"name":"SANKEN, Osaka University, Osaka, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8094-6861","authenticated-orcid":false,"given":"Longbiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5513-1192","authenticated-orcid":false,"given":"Guanglai","family":"Gao","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Inner Mongolia University, Hohhot, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511816338"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"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","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":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-134"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref12","first-page":"3171","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Ren","year":"2019"},{"key":"ref13","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Ren","year":"2021"},{"key":"ref14","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref15","first-page":"125","article-title":"WaveNet: A generative model for raw audio","volume-title":"Proc. 9th ISCA Speech Synth. Workshop","author":"Oord","year":"2016"},{"key":"ref16","first-page":"2410","article-title":"Efficient neural audio synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kalchbrenner","year":"2018"},{"key":"ref17","article-title":"Adversarial audio synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Donahue","year":"2019"},{"key":"ref18","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Kong","year":"2020"},{"key":"ref19","article-title":"The LJ speech dataset","author":"Ito","year":"2017"},{"key":"ref20","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. naacL-HLT","author":"Devlin","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3040523"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-36802-9_68"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/B0-08-044854-2\/02095-2"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IALP57159.2022.9961271"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-2401-1_28"},{"key":"ref26","first-page":"2448","article-title":"A LSTM approach with sub-word embeddings for Mongolian phrase break prediction","volume-title":"Proc. 27th Int. Conf. Comput. Linguistics","author":"Liu","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1706"},{"key":"ref28","first-page":"849","article-title":"Multi-speaker TTS system for low-resource language using cross-lingual transfer learning and data augmentation","volume-title":"Proc. IEEE Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf.","author":"Byambadorj","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-225"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.507"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403331"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746291"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-29516-5_5"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413466"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-17"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1251"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3148766"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1403"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1565"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2730"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2664"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-673"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.472"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1418"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3458380.3458405"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1757"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-621"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097074"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3177"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9054337"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1430"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3124365"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p16-1162"},{"key":"ref54","article-title":"RoBERTa: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3084827"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-97304-3_17"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054106"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3_4"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076369"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1080\/00223890802107925"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107337855"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.4337\/9781781003152.00014"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19551-8_23"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10379131.pdf?arnumber=10379131","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T04:46:28Z","timestamp":1706071588000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10379131\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3348762","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}