{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T05:20:54Z","timestamp":1768281654088,"version":"3.49.0"},"reference-count":26,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100000646","name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","doi-asserted-by":"publisher","award":["JP21H05054"],"award-info":[{"award-number":["JP21H05054"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000646","name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","doi-asserted-by":"publisher","award":["JP23K21681"],"award-info":[{"award-number":["JP23K21681"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001695","name":"Japan Science and Technology Agency (JST) Sakura Science Program and JST NEXUS","doi-asserted-by":"publisher","award":["JPMJNX25C1"],"award-info":[{"award-number":["JPMJNX25C1"]}],"id":[{"id":"10.13039\/501100001695","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2025.3644647","type":"journal-article","created":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T18:39:31Z","timestamp":1765823971000},"page":"2742-2752","source":"Crossref","is-referenced-by-count":0,"title":["SAM Translator: Self-Paced Learning And Mixture-of-Experts for Cross-Lingual Text-to-Speech Translation"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1268-3630","authenticated-orcid":false,"given":"Chung","family":"Tran","sequence":"first","affiliation":[{"name":"Nara Institute of Science and Technology, Ikoma, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5509-8963","authenticated-orcid":false,"given":"Sakriani","family":"Sakti","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology, Ikoma, Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3313513"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref3","first-page":"3450","article-title":"Multilingual translation with extensible multilingual pretraining and finetuning","author":"Tang","year":"2021","journal-title":"Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00343"},{"key":"ref5","first-page":"1189","article-title":"Self-paced learning for latent variable models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"23","author":"Kumar"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jml.2010.11.002"},{"key":"ref7","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","volume-title":"Proc. 5th Int. Conf. Learn. Represent.","author":"Shazeer"},{"issue":"120","key":"ref8","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref9","first-page":"8588","article-title":"FastSpeech2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. 9th Int. Learn. Represent.","author":"Ren"},{"key":"ref10","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479684"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1999-513"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3548429"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00618"},{"key":"ref17","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Skerry-Ryan"},{"key":"ref18","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst. Annu. Conf. Neural Inf. Process. Syst.","author":"Kong"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1160"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.221"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.411"},{"key":"ref22","first-page":"6691","article-title":"CVSS corpus and massively multilingual speech-to-speech translation","volume-title":"Proc. Language Resour. Eval. Conf. (LREC)","author":"Jia"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-2027"},{"key":"ref24","article-title":"Decoupled weight decay regularization","volume-title":"Proc. 7th Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref25","first-page":"8599","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Va"},{"key":"ref26","first-page":"186","article-title":"A call for clarity in reporting BLEU scores","volume-title":"Proc. 3rd Conf. Mach. Transl. Res. Papers","author":"Post"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11300906.pdf?arnumber=11300906","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:02:55Z","timestamp":1768255375000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11300906\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3644647","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}