{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T10:29:17Z","timestamp":1747909757316},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414081","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"5959-5963","source":"Crossref","is-referenced-by-count":5,"title":["One-Shot Voice Conversion Based on Speaker Aware Module"],"prefix":"10.1109","author":[{"given":"Ying","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Hao","family":"Che","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Li","sequence":"additional","affiliation":[]},{"given":"Chenxing","family":"Li","sequence":"additional","affiliation":[]},{"given":"Xiaorui","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Zhongyuan","family":"Wang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2365"},{"article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","year":"2018","author":"wang","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003844"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"article-title":"Aishell-2: transforming mandarin asr research into industrial scale","year":"2018","author":"du","key":"ref16"},{"key":"ref17","first-page":"5891","article-title":"Lpcnet: Improving neural speech synthesis through linear prediction","author":"valin","year":"2019","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-30"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref3","first-page":"369","article-title":"Voice conversion in high-order eigen space using deep belief nets","author":"nakashika","year":"2013","journal-title":"IEEE International Speech Communication Association"},{"article-title":"Acvae-vc: Non-parallel many-to- many voice conversion with auxiliary classifier variational autoencoder","year":"2018","author":"kameoka","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1504"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.2001-108","article-title":"High quality voice conversion based on gaussian mixture model with dynamic frequency warping","author":"toda","year":"2001"},{"key":"ref1","first-page":"4859","article-title":"Modulation spectrum- constrained trajectory training algorithm for gmm-based voice conversion","author":"takamichi","year":"2015","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref9","first-page":"4114","article-title":"Challenging common assumptions in the unsupervised learning of disentangled representations","author":"locatello","year":"2019","journal-title":"International Conference on Machine Learning"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414081.pdf?arnumber=9414081","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T08:31:36Z","timestamp":1672129896000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414081\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414081","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}