{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:27:03Z","timestamp":1764401223098,"version":"3.46.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001691","name":"JSPS Grant-in-Aid for Scientific Research","doi-asserted-by":"publisher","award":["JP23K21945,JP25K00471,JP23K20725"],"award-info":[{"award-number":["JP23K21945,JP25K00471,JP23K20725"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249275","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"2116-2121","source":"Crossref","is-referenced-by-count":0,"title":["CycleSiFiNF-VC: Controllable Non-Parallel Voice Conversion by Neural Formant Manipulation with Improved Cycle-Consistency Loss"],"prefix":"10.1109","author":[{"given":"Sumiharu","family":"Kobayashi","sequence":"first","affiliation":[{"name":"Tohoku University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takashi","family":"Nose","sequence":"additional","affiliation":[{"name":"Tohoku University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akinori","family":"Ito","sequence":"additional","affiliation":[{"name":"Tohoku University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414851"},{"key":"ref2","first-page":"5530","article-title":"Conditional Variational Autoencoder with Adversarial Learning for End-toEnd Text-to-Speech","volume-title":"Proc. ICML","author":"Kim","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-319"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref6","article-title":"ContentVec: An Improved SelfSupervised Speech Representation by Disentangling Speakers","volume-title":"Proc. ICML","author":"Qian","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1356"},{"key":"ref9","article-title":"YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for Everyone","volume-title":"Proc. ICML","author":"Casanova","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095191"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445804"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1432"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8682897"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/ecja.4400660203"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1622"},{"key":"ref16","first-page":"820","article-title":"End-toEnd Neural Formant Synthesis Using Low-Dimensional Acoustic Parameters","volume-title":"Proc. GCCE","author":"Kobayashi","year":"2024"},{"key":"ref17","first-page":"17 022","article-title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","volume-title":"Proc. NeurIPS","volume":"33","author":"Kong","year":"2020"},{"volume-title":"WaveNet: A Generative Model for Raw Audio","year":"2016","author":"van den Oord","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"volume-title":"Instance Normalization: The Missing Ingredient for Fast Stylization","year":"2017","author":"Ulyanov","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.207"},{"volume-title":"JVS corpus: Free Japanese multispeaker voice corpus","year":"2019","author":"Takamichi","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"volume-title":"Patch-Based Image Inpainting with Generative Adversarial Networks","year":"2018","author":"Demir","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095298"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249275.pdf?arnumber=11249275","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:24:12Z","timestamp":1764401052000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249275\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249275","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}