{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T17:23:36Z","timestamp":1769189016902,"version":"3.49.0"},"reference-count":80,"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"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100006378","name":"Pendampingan Publikasi Internasional (PPI) Q1 from Universitas Indonesia","doi-asserted-by":"publisher","award":["NKB-547\/UN2.RST\/HKP.05.00\/2021"],"award-info":[{"award-number":["NKB-547\/UN2.RST\/HKP.05.00\/2021"]}],"id":[{"id":"10.13039\/501100006378","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007065","name":"NVIDIA DGX-1 computing facilities at the Tokopedia-UI AI Center of Excellence","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007065","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3141200","type":"journal-article","created":{"date-parts":[[2022,1,7]],"date-time":"2022-01-07T20:33:48Z","timestamp":1641587628000},"page":"5895-5911","source":"Crossref","is-referenced-by-count":14,"title":["Transfer Learning, Style Control, and Speaker Reconstruction Loss for Zero-Shot Multilingual Multi-Speaker Text-to-Speech on Low-Resource Languages"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3217-7025","authenticated-orcid":false,"given":"Kurniawati","family":"Azizah","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0530-7955","authenticated-orcid":false,"given":"Wisnu","family":"Jatmiko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref2","first-page":"6270","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","volume":"9","author":"Van Den Oord"},{"key":"ref3","first-page":"264","article-title":"Deep voice: Real-time neural text-to-speech","volume-title":"Proc. 34th Int. Conf. Mach. Learn. (ICML)","volume":"1","author":"Arik"},{"key":"ref4","first-page":"2963","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Arik"},{"key":"ref5","first-page":"1","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Ping"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682353"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2935807"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/info10040131"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/app9194050"},{"key":"ref12","first-page":"5932","article-title":"Fitting new speakers based on a short untranscribed sample","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","volume":"8","author":"Nachmani"},{"key":"ref13","article-title":"Multi-speaker end-to-end speech synthesis","author":"Park","year":"2019","journal-title":"arXiv:1907.04462"},{"key":"ref14","first-page":"1","article-title":"Sample efficient adaptive text-to-speech","volume-title":"Proc. 7th Int. Conf. Learn. Represent. (ICLR)","author":"Chen"},{"key":"ref15","article-title":"Modeling multi-speaker latent space to improve neural TTS: Quick enrolling new speaker and enhancing premium voice","author":"Deng","year":"2019","journal-title":"arXiv:1812.05253v4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1558"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639659"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-5"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3027619"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref21","first-page":"4485","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume-title":"Proc. 32nd Conf. Neural Inf. Process. Syst. (NIPS)","author":"Jia"},{"key":"ref22","article-title":"Cross-lingual multi-speaker text-to-speech synthesis for voice cloning without using parallel corpus for unseen speakers","author":"Liu","year":"2019","journal-title":"arXiv:1911.11601"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1032"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.201"},{"key":"ref25","first-page":"7","article-title":"Natural language processing for less privileged languages: Where do we come from? Where are we going?","volume-title":"Proc. IJCNLP Workshop NLP Less Privileged Lang.","author":"Singh"},{"key":"ref26","first-page":"4543","article-title":"Selection criteria for low resource language programs","volume-title":"Proc. 10th Int. Conf. Lang. Resour. Eval.","author":"Cieri"},{"key":"ref27","volume-title":"The 4 Biggest Open Problems in NLP","author":"Ruder","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICACSIS51025.2020.9263086"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref30","volume-title":"The #BenderRule: On naming the languages we study and why it matters. The Gradient","author":"Bender","year":"2019"},{"key":"ref31","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Goodfellow"},{"key":"ref32","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn. (ICML)","volume":"70","author":"Finn"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-016-0043-6"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01424-7_27"},{"key":"ref36","article-title":"Low-resource languages: A review of past work and future challenges","author":"Magueresse","year":"2020","journal-title":"arXiv:2006.07264"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683862"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268950"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639672"},{"key":"ref40","first-page":"131","article-title":"Cross-lingual machine speech chain for Javanese, Sundanese, Balinese, and Bataks speech recognition and synthesis","volume-title":"Proc. 1st Joint Spoken Lang. Technol. Under-Resour. Lang. (SLTU)","author":"Novitasari"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2730"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10470-017-1069-1"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/I2CT.2018.8529519"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3311\/ppee.17024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2713"},{"issue":"8","key":"ref46","first-page":"956","article-title":"A review on speaker verification: Challenges and issues","volume":"8","author":"Sreedharan","year":"2019","journal-title":"Int. J. Sci. Technol. Res."},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"issue":"9","key":"ref48","first-page":"1","article-title":"Deep speaker vectors for semi text-independent speaker verification","volume":"13","author":"Li","year":"2015","journal-title":"J. Latex Class Files"},{"key":"ref49","article-title":"Deep speaker: An end-to-end neural speaker embedding system","author":"Li","year":"2017","journal-title":"arXiv:1705.02304"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-620"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.2991\/anit-17.2018.21"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2205"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1891"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023039"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404779"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1545"},{"key":"ref59","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (PMLR)","volume":"80","author":"Wang"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1924"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053110"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054578"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.3390\/app10082884"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076369"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref68","volume-title":"The LJ Speech Dataset 2017","author":"Ito","year":"2017"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref70","first-page":"17","article-title":"A large vocabulary continuous speech recognition system for Indonesian language","volume-title":"Proc. 15th Indonesian Sci. Conf. Jpn.","author":"Lestari"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.21437\/SLTU.2018-14"},{"key":"ref72","volume-title":"Tacotron 2 Without WaveNet","year":"2018"},{"key":"ref73","volume-title":"WaveGlow","year":"2018"},{"key":"ref74","volume-title":"Speaker Encoder","year":"2020"},{"key":"ref75","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2003.1318504"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref79","article-title":"UMAP: Uniform manifold approximation and projection for dimension reduction","author":"McInnes","year":"2018","journal-title":"arXiv:1802.03426"},{"issue":"1","key":"ref80","first-page":"2579","article-title":"Visualizing data using t-SNE Laurens","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09673749.pdf?arnumber=9673749","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T22:19:54Z","timestamp":1705184394000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9673749\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3141200","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}