{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T09:12:01Z","timestamp":1790413921461,"version":"4.1.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747272","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6572-6576","source":"Crossref","is-referenced-by-count":29,"title":["Robust Disentangled Variational Speech Representation Learning for Zero-Shot Voice Conversion"],"prefix":"10.1109","author":[{"given":"Jiachen","family":"Lian","sequence":"first","affiliation":[{"name":"UC Berkeley, EECS,CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunlei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Bellevue,WA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Bellevue,WA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1","article-title":"Phonetic posteriorgrams for many-to-one voice conversion without parallel data training","author":"sun","year":"2016","journal-title":"2016 IEEE International Conference on Multimedia and Expo (ICME)"},{"key":"ref11","article-title":"Phonetic posteriorgrams based many-to-many singing voice conversion via adversarial training","author":"guo","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066047"},{"key":"ref13","first-page":"5210","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","author":"qian","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref15","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014"},{"key":"ref16","article-title":"Disentangled sequential autoencoder","author":"li","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00657"},{"key":"ref18","article-title":"Lagging inference networks and posterior collapse in variational autoencoders","author":"he","year":"2019"},{"key":"ref19","article-title":"Deep variational information bottleneck","author":"alemi","year":"2016"},{"key":"ref28","article-title":"Visualizing data using t-sne","volume":"9","author":"der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref27","article-title":"Musan: A music, speech, and noise corpus","author":"snyder","year":"2015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1789"},{"key":"ref6","first-page":"359","article-title":"Using dynamic time warping to find patterns in time series","volume":"10","author":"berndt","year":"1994","journal-title":"KDD Workshop"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2892235"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-36"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref1","article-title":"An overview of voice conversion and its challenges: From statistical modeling to deep learning","author":"sisman","year":"2020","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref20","article-title":"Gradient surgery for multi-task learning","author":"yu","year":"2020"},{"key":"ref22","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","author":"veaux","year":"2017"},{"key":"ref21","article-title":"Timit acoustic phonetic continuous speech corpus","author":"garofolo","year":"1993","journal-title":"Linguistic Data Consortium 1993"},{"key":"ref24","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"ulyanov","year":"2016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref26","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","author":"hsu","year":"2017"},{"key":"ref25","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747272.pdf?arnumber=9747272","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:10:04Z","timestamp":1661199004000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747272\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747272","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}