{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T05:27:37Z","timestamp":1738128457980,"version":"3.33.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2024,12,3]]},"DOI":"10.1109\/apsipaasc63619.2025.10848687","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:37:05Z","timestamp":1738003025000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["PPHiFi-TTS: Phonetic Preserved High-Fidelity Text-to-Speech for Long-Term Speech Dependencies"],"prefix":"10.1109","author":[{"given":"Ravindrakumar M.","family":"Purohit","sequence":"first","affiliation":[{"name":"Research Lab,DAIICT,Gandhinagar,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dharmendra H.","family":"Vaghera","sequence":"additional","affiliation":[{"name":"Research Lab,DAIICT,Gandhinagar,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arth J.","family":"Shah","sequence":"additional","affiliation":[{"name":"Research Lab,DAIICT,Gandhinagar,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hemant A.","family":"Patil","sequence":"additional","affiliation":[{"name":"Research Lab,DAIICT,Gandhinagar,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"A generative model for raw audio","year":"2016","author":"van den Oord","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","year":"2020","author":"Ren","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref6","first-page":"8067","article-title":"A generative flow for text-to-speech via monotonic alignment search","volume-title":"Advances in Neural Information Processing Systems (NIPS)","volume":"33","author":"Kim"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10294"},{"key":"ref10","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","volume-title":"Advances in Neural Information Processing Systems (NIPS)","volume":"30","author":"Gibiansky","year":"2017"},{"key":"ref11","first-page":"17022","article-title":"Hifi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in Neural Information Processing Systems(NIPS), Vancouver, Canada"},{"key":"ref12","first-page":"2672","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume":"32","author":"Kumar","year":"2019","journal-title":"Advances in Neural Information Processing Systems (NIPS), Vancouver, Canada"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03958"},{"volume-title":"The LJ Speech Dataset","year":"2017","author":"Ito","key":"ref14"},{"article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","year":"2019","author":"Yamagishi","key":"ref15"},{"key":"ref16","first-page":"1774","article-title":"Measuring a speaker\u2019s acoustic correlates of pitch but which a contrastive analysis for perceived speaker charisma","volume-title":"19th International Congress of Phonetic Sciences: Endangered Languages, and Major Language Varieties (ICPhS)","author":"Niebuhr"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-014-0446-1"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"}],"event":{"name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2024,12,3]]},"location":"Macau, Macao","end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10848542\/10848533\/10848687.pdf?arnumber=10848687","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:18:53Z","timestamp":1738045133000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10848687\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc63619.2025.10848687","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}