{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:51:22Z","timestamp":1764399082158,"version":"3.46.0"},"reference-count":31,"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\/apsipaasc65261.2025.11249053","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"867-872","source":"Crossref","is-referenced-by-count":0,"title":["Gamma-VAE-VC: Voice Conversion based on VAE Assuming Gamma Distribution for Both Latent Variables and Observation"],"prefix":"10.1109","author":[{"given":"Nanako","family":"Imaichi","sequence":"first","affiliation":[{"name":"University of Electro-communications,Chofu,Tokyo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takuya","family":"Takahashi","sequence":"additional","affiliation":[{"name":"University of Electro-communications,Chofu,Tokyo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Toru","family":"Nakashika","sequence":"additional","affiliation":[{"name":"University of Electro-communications,Chofu,Tokyo"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.05.001"},{"key":"ref4","first-page":"1","article-title":"Singing voice conversion method based on many-to-many eigenvoice conversion and training data generation using a singing-to-singing synthesis system","volume-title":"Proceedings of The 2012 Asia Pacific Signal and Information Processing Association Annual Summit and Conference","author":"Doi"},{"key":"ref5","article-title":"Cross-lingual text-to-speech using multi-task learning and speaker classifier joint training","author":"Yang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461384"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-017-0116-2"},{"key":"ref9","article-title":"A statistical model of timbre perception","volume":"5","author":"Terasawa","year":"2006","journal-title":"SAPA @ INTERSPEECH"},{"journal-title":"Information processing in dynamical systems: Foundations of harmony theory","year":"1986","author":"Smolensky","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2353991"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.E97.D.1403"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2047683"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-447"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref16","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-970"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2236"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2917232"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref22","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC63619.2025.10848612"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref25","first-page":"186","article-title":"An application of the principle of maximum information preservation to linear systems","volume":"1","author":"Linske","year":"1989","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","first-page":"2","article-title":"Elbo surgery: Yet another way to carve up the variational evidence lower bound","volume-title":"Workshop in Advances in Approximate Bayesian Inferenc","volume":"1","author":"Hoffman"},{"key":"ref27","first-page":"299","article-title":"On information-type measure of difference of probability distributions and indirect observations","volume":"2","author":"Csisz\u00e1r","year":"1967","journal-title":"Studia Sci. Math. Hungar."},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1527\/tjsai.36-3_A-KA4"},{"key":"ref29","first-page":"271","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019","journal-title":"University of Edinburgh. The Centre for Speech Technology Research (CSTR)"},{"key":"ref30","article-title":"Algorithms for non-negative matrix factorization","volume":"13","author":"Lee","year":"2000","journal-title":"Advances in neural information processing systems"},{"article-title":"Beta-vae: Learning basic visual concepts with a constrained variational framework","volume-title":"International conference on learning representations","author":"Higgins","key":"ref31"}],"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\/11249053.pdf?arnumber=11249053","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:50:06Z","timestamp":1764399006000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249053\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249053","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}