{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:01:21Z","timestamp":1764399681463,"version":"3.46.0"},"reference-count":25,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249172","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"813-818","source":"Crossref","is-referenced-by-count":0,"title":["VICNet: FaderNet-Based Voice Impression Conversion with Affective Dimensional Representation"],"prefix":"10.1109","author":[{"given":"Takuya","family":"Takahashi","sequence":"first","affiliation":[{"name":"The University of Electro-Communications,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saki","family":"Kugimoto","sequence":"additional","affiliation":[{"name":"The University of Electro-Communications,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Toru","family":"Nakashika","sequence":"additional","affiliation":[{"name":"The University of Electro-Communications,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-017-9430-4"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414757"},{"key":"ref3","article-title":"Voice gender conversion with speaker identity preservation based on FaderNets","volume-title":"Dissertation at University of ElectroCommunications","author":"Kuwabara","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446191"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1317"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29902"},{"key":"ref7","article-title":"Voice impression transformation based on FaderNets with impression expression word labels","volume-title":"Dissertation at University of ElectroCommunications","author":"Okadome","year":"2022"},{"issue":"21","key":"ref8","first-page":"1","article-title":"Voice impression conversion for unseen speakers using FaderNets","volume-title":"Proceedings of the Spoken Language Processing in Information Processing Society of Japan","volume":"2023","author":"Kugimoto","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.2466\/pms.1974.38.1.283"},{"issue":"5","key":"ref10","first-page":"337","article-title":"Everyday expressions associated with vioce quiality of normal utterance-extraction by perceptual evaluation-","volume":"57","author":"Kido","year":"2001","journal-title":"The Journal of the Acoustical Society of Japan"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1316511.1316516"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-41248-6_13"},{"key":"ref14","article-title":"Music FaderNets: Controllable music generation based on high-level features via low-level feature modelling","author":"Tan","year":"2020","journal-title":"arXiv preprint"},{"key":"ref15","first-page":"741","article-title":"Emotion-driven harmonisation and tempo arrangement of melodies using transfer learning.","volume-title":"International Society for Music Information Retrieval Conference","author":"Takahashi","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-012-0314-x"},{"key":"ref17","article-title":"JVS corpus: Free Japanese multi-speaker voice corpus","author":"Takamichi","year":"2019","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/0005-7916(94)90063-9"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-012-0310-1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367262"},{"key":"ref22","article-title":"Deep fuzzy framework for emotion recognition using eeg signals and emotion representation in type2 fuzzy vad space","author":"Asif","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136760"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2020.14"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-124"}],"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\/11249172.pdf?arnumber=11249172","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:57:23Z","timestamp":1764399443000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249172\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249172","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}