{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T06:51:52Z","timestamp":1767077512391,"version":"3.48.0"},"reference-count":46,"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"}],"funder":[{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","award":["JPMJBS2410"],"award-info":[{"award-number":["JPMJBS2410"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3647153","type":"journal-article","created":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T18:42:48Z","timestamp":1766428968000},"page":"216583-216595","source":"Crossref","is-referenced-by-count":0,"title":["Sequence-to-Sequence Voice Conversion With Weighted Guided Attention"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8553-9317","authenticated-orcid":false,"given":"Haruki","family":"Yamashita","sequence":"first","affiliation":[{"name":"Graduate School of System Informatics, Kobe University, Kobe, 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\/0000-0002-9808-0250","authenticated-orcid":false,"given":"Ryoichi","family":"Takashima","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Ritsumeikan University, Ibaraki, 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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5005-7679","authenticated-orcid":false,"given":"Tetsuya","family":"Takiguchi","sequence":"additional","affiliation":[{"name":"Graduate School of System Informatics, Kobe University, Kobe, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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":"10.1016\/j.specom.2017.01.008"},{"key":"ref2","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. NIPS","author":"Goodfellow"},{"key":"ref3","article-title":"Parallel-Data-Free voice conversion using cycle-consistent adversarial networks","author":"Kaneko","year":"2017","journal-title":"arXiv:1711.11293"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414851"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2236"},{"key":"ref6","article-title":"WaveCycleGAN2: Time-domain neural post-filter for speech waveform generation","author":"Tanaka","year":"2019","journal-title":"arXiv:1904.02892"},{"key":"ref7","first-page":"1","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2917232"},{"key":"ref9","first-page":"5210","article-title":"AutoVC: Zero-shot voice style transfer with only autoencoder loss","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qian"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-947"},{"key":"ref11","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","volume":"33","author":"Ho"},{"key":"ref12","article-title":"Diffusion-based voice conversion with fast maximum likelihood sampling scheme","author":"Popov","year":"2021","journal-title":"arXiv:2109.13821"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-250"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29740"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2892235"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054523"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3047262"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1066"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3049336"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3577374"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3369528"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3156757"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2025.3530920"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2383"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1211.3711"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747707"},{"key":"ref28","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":"ref29","first-page":"1","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Ren"},{"key":"ref30","first-page":"1","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. ICLR","author":"Ren"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10294"},{"key":"ref32","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":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2518"},{"key":"ref34","article-title":"AAS-VC: On the generalization ability of automatic alignment search based non-autoregressive sequence-to-sequence voice conversion","author":"Huang","year":"2023","journal-title":"arXiv:2309.07598"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446191"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-700"},{"key":"ref37","first-page":"223","article-title":"The CMU Arctic speech databases","volume-title":"Proc. 5th ISCA Workshop Speech Synth. (SSW 5)","author":"Kominek"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1110"},{"volume-title":"Hi-Fi-Captain: High-Fidelity and High-Capacity Conversational Speech Synthesis Corpus Developed By NICT","year":"2023","author":"Okamoto","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref41","article-title":"ESPnet2-TTS: Extending the edge of TTS research","author":"Hayashi","year":"2021","journal-title":"arXiv:2110.07840"},{"key":"ref42","first-page":"8024","article-title":"PyTorch: An imperative style, \"PyTorch: An imperative style","volume-title":"Proc. NeurIPS","author":"Paszke"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3366707"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref45","first-page":"7","article-title":"Corpus of spontaneous Japanese: Its design and evaluation","volume-title":"Proc. ISCA IEEE Workshop Spontaneous Speech Process. Recognit.","author":"Maekawa"},{"volume-title":"Silero VAD: Pre-Trained Enterprise-Grade Voice Activity Detector (vad)","year":"2024","key":"ref46"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11311535.pdf?arnumber=11311535","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T06:49:31Z","timestamp":1767077371000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11311535\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3647153","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}