{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T15:15:53Z","timestamp":1767626153242,"version":"3.28.0"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"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":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892169","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-8","source":"Crossref","is-referenced-by-count":3,"title":["Speaker Characteristics Guided Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Zhihan","family":"Yang","sequence":"first","affiliation":[{"name":"Shenzhen International Graduate School Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Jia","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Normalizing flows: An introduction and review of current methods","author":"kobyzev","year":"2020","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref38","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref31","article-title":"Multi-speaker end-to-end speech synthesis","author":"park","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref30","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","author":"arik","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1620"},{"key":"ref35","article-title":"Semi-supervised generative modeling for controllable speech synthesis","author":"habib","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1037\/h0060838"},{"journal-title":"Voice and personality","year":"1931","author":"pear","key":"ref27"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1002\/ejsp.2420080405"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2007.10.001"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2003.09.005"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.2601.22"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.biopsycho.2005.09.003"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2018.01.006"},{"key":"ref24","volume":"4","author":"sanderson","year":"2008","journal-title":"Biometric Person Recognition Face Speech and Fusion"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/S0165-5876(99)00208-6"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1086\/214279"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00772"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1044\/1092-4388(2010\/10-0036)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.bjorl.2017.04.003"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1080\/00224545.1976.9924774"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.1901.168"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S0892-1997(98)80022-2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_32"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1121\/1.1352085"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/1474704916630317"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2096"},{"key":"ref3","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053436"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053520"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2136"},{"key":"ref7","article-title":"Hierarchical generative modeling for controllable speech synthesis","author":"hsu","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref49","article-title":"Conditional generative adversarial nets","author":"mirza","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1001\/archotol.1980.00790270013003"},{"key":"ref46","article-title":"Big five inventory","author":"john","year":"1991","journal-title":"Journal of Personality and Social Psychology"},{"key":"ref45","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref42","article-title":"Glow: Generative flow with invertible 1&#x00D7;1 convolutions","author":"kingma","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref41","article-title":"Masked autoregressive flow for density estimation","author":"papamakarios","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref44","article-title":"Recent developments on espnet toolkit boosted by conformer","author":"guo","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref43","first-page":"5329","article-title":"X-vectors: Robust dnn embeddings for speaker recognition","author":"snyder","year":"0","journal-title":"2018 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2022,7,18]]},"location":"Padua, Italy","end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892169.pdf?arnumber=9892169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T22:59:59Z","timestamp":1667516399000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892169\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892169","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}