{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T07:13:48Z","timestamp":1771485228640,"version":"3.50.1"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"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":[],"published-print":{"date-parts":[[2025,11,12]]},"DOI":"10.1109\/o-cocosda68185.2025.11384822","type":"proceedings-article","created":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T21:14:09Z","timestamp":1771449249000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["HifiDiff: Two Stream Diffusion Models for High Fidelity Speech Generation of Unseen Languages"],"prefix":"10.1109","author":[{"given":"Lhuqita","family":"Fazry","sequence":"first","affiliation":[{"name":"University of Indonesia,Indonesia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kurniawati","family":"Azizah","sequence":"additional","affiliation":[{"name":"University of Indonesia,Indonesia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dipta","family":"Tanaya","sequence":"additional","affiliation":[{"name":"University of Indonesia,Indonesia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ayu","family":"Purwarianti","sequence":"additional","affiliation":[{"name":"Bandung Institute of Technology,Indonesia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dessi","family":"Lestari","sequence":"additional","affiliation":[{"name":"Bandung Institute of Technology,Indonesia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sakriani","family":"Sakti","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1561\/2000000001"},{"key":"ref2","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014","journal-title":"in NIPS"},{"key":"ref3","article-title":"Auto-encoding variational bayes","volume":"abs\/1312.6114","author":"Kingma","year":"2013","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref5","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"in Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16859-3_42"},{"key":"ref7","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proceedings of the 32nd International Conference on Machine Learning","author":"Sohl-Dickstein"},{"key":"ref8","article-title":"Diffusion models beat gans on image synthesis","volume-title":"in Advances in Neural Information Processing Systems","author":"Dhariwal","year":"2021"},{"key":"ref9","article-title":"Diffwave: A versatile diffusion model for audio synthesis","volume-title":"International Conference on Learning Representations","author":"Kong"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1897"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462417"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2970241"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9053795"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3051765"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414401"},{"key":"ref17","article-title":"Sliced score matching: A scalable approach to density and score estimation","volume-title":"Conference on Uncertainty in Artificial Intelligence","author":"Song"},{"key":"ref18","author":"Popov","year":"2021","journal-title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746690"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP57327.2022.10038120"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1424"},{"key":"ref22","author":"Lee","year":"2022","journal-title":"Bigvgan: A universal neural vocoder with large-scale training"},{"key":"ref23","article-title":"Neural networks fail to learn periodic functions and how to fix it","author":"Ziyin","year":"2020","journal-title":"in NeurIPS"},{"key":"ref24","article-title":"Rectified linear units improve restricted boltzmann machines","author":"Nair","year":"2010","journal-title":"in ICML"},{"key":"ref25","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"in Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSP49548.2020.9163446"},{"key":"ref29","volume-title":"The lj speech dataset","author":"Ito","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1139"},{"key":"ref31","article-title":"Crowdsourcing Latin American Spanish for Low-Resource Text-to-Speech","volume-title":"Proceedings of The 12th LREC","author":"Guevara-Rukoz"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2020-152"},{"key":"ref33","article-title":"Cross-lingual machine speech chain for Javanese, Sundanese, Balinese, and Bataks speech recognition and synthesis","volume-title":"in Proc. Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)","author":"Novitasari","year":"2020"}],"event":{"name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","location":"Yogyakarta, Indonesia","start":{"date-parts":[[2025,11,12]]},"end":{"date-parts":[[2025,11,14]]}},"container-title":["2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11383559\/11384821\/11384822.pdf?arnumber=11384822","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T06:45:25Z","timestamp":1771483525000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11384822\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,12]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/o-cocosda68185.2025.11384822","relation":{},"subject":[],"published":{"date-parts":[[2025,11,12]]}}}