{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:28:34Z","timestamp":1775230114921,"version":"3.50.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3585135","type":"journal-article","created":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T13:45:39Z","timestamp":1751463939000},"page":"118369-118380","source":"Crossref","is-referenced-by-count":1,"title":["Phoneme-Level Duration Controllable Neural Text-to-Speech With Phoneme Embedding Skip Connection and Modified Gaussian Duration Modeling"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4507-0008","authenticated-orcid":false,"given":"Tadashi","family":"Ogura","sequence":"first","affiliation":[{"name":"National Institute of Information and Communications Technology, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9913-4647","authenticated-orcid":false,"given":"Takuma","family":"Okamoto","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2961-2821","authenticated-orcid":false,"given":"Yamato","family":"Ohtani","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erica","family":"Cooper","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8146-1279","authenticated-orcid":false,"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0914-5092","authenticated-orcid":false,"given":"Hisashi","family":"Kawai","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref2","first-page":"3915","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","volume-title":"Proc. ICML","author":"van den Oord"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref5","first-page":"3165","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume-title":"Proc. NeurIPS","author":"Ren"},{"key":"ref6","article-title":"FastSpeech2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. ICLR","author":"Ren"},{"key":"ref7","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS","author":"Kong"},{"key":"ref8","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":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10294"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022496"},{"key":"ref11","first-page":"2709","article-title":"YourTTS: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume-title":"Proc. ICML","author":"Casanova"},{"key":"ref12","article-title":"NaturalSpeech2: Latent diffusion models are natural and zero-shot speech and singing synthesizers","volume-title":"Proc. ICLR","author":"Shen"},{"key":"ref13","article-title":"End-to-end adversarial text-to-speech","volume-title":"Proc. ICLR","author":"Donahue"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413851"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-831"},{"key":"ref16","first-page":"276","article-title":"Maximum listening speeds for the blind","volume-title":"Proc. ICAD","author":"Asakawa"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.3606.1276"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1250\/ast.39.92"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319366"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162810"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.01.003"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.5.825"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003956"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414718"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1461"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683827"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1361"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1997-160"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607301"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.1998-6"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747158"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3366707"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095431"},{"key":"ref35","volume-title":"Hi-Fi-CAPTAIN: High-fidelity and High-Capacity Conversational Speech Synthesis Corpus Developed by NICT","author":"Okamoto","year":"2023"},{"key":"ref36","volume-title":"Methods for Subjective Determination Transmission Quality","year":"1996"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639215"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref42","article-title":"ESPnet2-TTS: Extending the edge of TTS research","author":"Hayashi","year":"2021","journal-title":"arXiv:2110.07840"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747707"},{"key":"ref45","first-page":"8067","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","volume-title":"Proc. NeurIPS","author":"Kim"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446890"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1121\/1.4919349"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389765"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688194"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746713"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095296"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3390\/app6020057"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/slt.2016.7846338"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-68"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2020EDP7104"},{"key":"ref57","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. NeurIPS","author":"Paszke"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref59","first-page":"7","article-title":"Corpus of spontaneous Japanese: Its design and evaluation","volume-title":"Proc. IEEE Workshop Spontaneous Speech Process. Recognit. (ISCA)","author":"Maekawa"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11062880.pdf?arnumber=11062880","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T05:36:02Z","timestamp":1752557762000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11062880\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3585135","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}