{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:04:01Z","timestamp":1764403441355,"version":"3.33.0"},"reference-count":24,"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\/apsipaasc63619.2025.10849015","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":2,"title":["DDPMVC: Non-parallel any-to-many voice conversion using diffusion encoder"],"prefix":"10.1109","author":[{"given":"Ryuichi","family":"Hatakeyama","sequence":"first","affiliation":[{"name":"The University of Electro-Communications,Tokyo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kohei","family":"Okuda","sequence":"additional","affiliation":[{"name":"The University of Electro-Communications,Tokyo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Toru","family":"Nakashika","sequence":"additional","affiliation":[{"name":"The University of Electro-Communications,Tokyo"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Auto-encoding variational bayes","year":"2022","author":"Kingma","key":"ref1"},{"key":"ref2","article-title":"Generative adversarial nets","volume-title":"Advances in Neural Information Processing Systems","volume":"27","author":"Goodfellow","year":"2014"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/asru51503.2021.9688219"},{"journal-title":"Diffusion-based voice conversion with fast maximum likelihood sampling scheme","year":"2022","author":"Popov","key":"ref4"},{"volume-title":"Voicegrad: Non-parallel any-to-many voice conversion with annealed langevin dynamics","year":"2024","author":"Kameoka","key":"ref5"},{"key":"ref6","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proceedings of the 32nd International Conference on Machine Learning","volume":"37","author":"Sohl-Dickstein"},{"key":"ref7","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Ho","year":"2020"},{"key":"ref8","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Song","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-63"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_00142"},{"article-title":"Score-based generative modeling through stochastic differential equations","year":"2021","author":"Song","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4149(82)90051-5"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1017\/9781108186735"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2015.06.002"},{"volume-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"Kong","key":"ref15"},{"article-title":"The CMU arctic speech databases","volume-title":"Fifth ISCA workshop on speech synthesis","author":"Kominek","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015edp7457"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2010.5495701"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1542"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icme.2016.7552917"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9415079"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413699"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1356"}],"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\/10849015.pdf?arnumber=10849015","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:23:59Z","timestamp":1738045439000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10849015\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc63619.2025.10849015","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}