{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T22:42:37Z","timestamp":1765233757969,"version":"3.37.3"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100015843","name":"NAV","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015843","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448471","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12186-12190","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing Multilingual TTS with Voice Conversion Based Data Augmentation and Posterior Embedding"],"prefix":"10.1109","author":[{"given":"Hyun-Wook","family":"Yoon","sequence":"first","affiliation":[{"name":"NAVER Cloud,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin-Seob","family":"Kim","sequence":"additional","affiliation":[{"name":"NAVER Cloud,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryuichi","family":"Yamamoto","sequence":"additional","affiliation":[{"name":"LINE Corp.,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryo","family":"Terashima","sequence":"additional","affiliation":[{"name":"LINE Corp.,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chan-Ho","family":"Song","sequence":"additional","affiliation":[{"name":"NAVER Cloud,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jae-Min","family":"Kim","sequence":"additional","affiliation":[{"name":"NAVER Cloud,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eunwoo","family":"Song","sequence":"additional","affiliation":[{"name":"NAVER Cloud,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref2","first-page":"8599","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. ICML","author":"Popov"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3356232\/mm1"},{"key":"ref4","first-page":"8067","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","author":"Kim","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. ICML","author":"Kim"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2730"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2070"},{"article-title":"Cross-lingual text-to-speech using multitask learning and speaker classifier joint training","year":"2022","author":"Yang","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1590"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-017-0659-6"},{"article-title":"Building multilingual TTS using cross lingual voice conversion","year":"2020","author":"Sun","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746282"},{"article-title":"Deep Voice 2: Multi-speaker neural text-to-speech","volume-title":"Proc. NeurIPS","author":"Gibiansky","key":"ref13"},{"article-title":"Auto-encoding variational bayes","volume-title":"Proc. ICLR","author":"Kingma","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1113"},{"key":"ref16","first-page":"16 624","article-title":"HierSpeech: Bridging the gap between text and speech by hierarchical variational inference using self-supervised representations for speech synthesis","volume-title":"Proc. NeurIPS","author":"Lee"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053726"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11278"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1017\/9780511807954"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10134"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/nbt1206-1565"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003956"},{"article-title":"Non-attentive Tacotron: Robust and controllable neural TTS synthesis including unsupervised duration modeling","year":"2020","author":"Shen","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11133"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1288"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448471.pdf?arnumber=10448471","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:54:21Z","timestamp":1722660861000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448471\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448471","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}