{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T16:26:59Z","timestamp":1779208019219,"version":"3.51.4"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100006378","name":"Universitas Indonesia through the Publikasi Terindeks International (PUTI) Doktor","doi-asserted-by":"publisher","award":["NKB-566\/UN2.RST\/HKP.05.00\/2020"],"award-info":[{"award-number":["NKB-566\/UN2.RST\/HKP.05.00\/2020"]}],"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":[[2020]]},"DOI":"10.1109\/access.2020.3027619","type":"journal-article","created":{"date-parts":[[2020,9,29]],"date-time":"2020-09-29T20:55:55Z","timestamp":1601412955000},"page":"179798-179812","source":"Crossref","is-referenced-by-count":26,"title":["Hierarchical Transfer Learning for Multilingual, Multi-Speaker, and Style Transfer DNN-Based TTS on Low-Resource Languages"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3217-7025","authenticated-orcid":false,"given":"Kurniawati","family":"Azizah","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mirna","family":"Adriani","sequence":"additional","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":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2889606"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682918"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-016-0043-6"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"jialin pan","year":"2010","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2730"},{"key":"ref30","first-page":"131","article-title":"Cross-lingual machine speech chain for Javanese, Sundanese, Balinese, and Bataks speech recognition and synthesis","author":"novitasari","year":"2020","journal-title":"Proc Workshop Spoken Lang Technol for Under-Resourced Lang (SLTU)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1176"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2936002"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/app10062021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SIPROCESS.2018.8600536"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.09.003"},{"key":"ref61","first-page":"3969","article-title":"Reducing f0 frame error of f0 tracking algorithms under noisy conditions with an unvoiced\/voiced classification frontend","author":"chu","year":"2009","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268950"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683862"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639672"},{"key":"ref2","author":"jurasfky","year":"2009","journal-title":"Speech and Language Processing An Introduction to Natural Language Processing Computational Linguistics and Speech Recognition"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.11.001"},{"key":"ref20","first-page":"1","article-title":"Deep Voice 3: Scaling text-to-speech with convolutional sequence learning","author":"ping","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)ICLR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/info10040131"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2935807"},{"key":"ref24","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"arXiv 1803 09017"},{"key":"ref23","first-page":"7471","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume":"11","author":"skerry-ryan","year":"2018","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01424-7_27"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054556"},{"key":"ref50","author":"ito","year":"2017","journal-title":"The LJ Speech Dataset 2017"},{"key":"ref51","first-page":"17","article-title":"A large vocabulary continuous speech recognition system for Indoneia Language","author":"lestari","year":"2006","journal-title":"15th Indones Sci Conf Japan Proc"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref58","first-page":"577","article-title":"Is word error rate a good indicator for spoken language understanding accuracy","author":"wang","year":"2003","journal-title":"Proc IEEE Workshop Autom Speech Recognition Understanding (ASRU)"},{"key":"ref57","first-page":"381","article-title":"The SUS test: A method for the assessment of text-to-speech synthesis intelligibility using semantically unpredictable sentences","volume":"6393","author":"grice","year":"1996","journal-title":"Speech Commun"},{"key":"ref56","year":"2018","journal-title":"Waveglow"},{"key":"ref55","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent (Poster)"},{"key":"ref54","year":"2018","journal-title":"Tacotron 2 Without WaveNet"},{"key":"ref53","author":"paszke","year":"2020","journal-title":"PyTorch"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/SLTU.2018-14"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/electronics8030292"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.12400"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3390\/sym11020179"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2912200"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682353"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref17","first-page":"6270","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","volume":"9","author":"van den oord","year":"2018","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref18","first-page":"264","article-title":"Deep voice: Real-time neural text-to-speech","volume":"1","author":"arik","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref19","first-page":"2963","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","author":"arik","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/app9194050"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511816338"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2006647"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref8","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"Proc 38th IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2905167"},{"key":"ref49","first-page":"10215","article-title":"Glow: Generative flow with invertible $1\\times1$\n convolutions","author":"kingma","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.08.003"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1121\/1.1458024"},{"key":"ref45","article-title":"Hierarchical transfer learning for text-to-speech in Indonesian, Javanese, and Sundanese languages","author":"azizah","year":"2020","journal-title":"Proc Int Conf Adv Comput Sci Inf Syst"},{"key":"ref48","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc ICLR"},{"key":"ref47","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3390\/a10030081"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2019.8918833"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref43","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09208651.pdf?arnumber=9208651","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:56:15Z","timestamp":1639770975000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9208651\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3027619","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}