{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:14:03Z","timestamp":1776885243273,"version":"3.51.2"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T00:00:00Z","timestamp":1693785600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T00:00:00Z","timestamp":1693785600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,9,4]]},"DOI":"10.23919\/eusipco58844.2023.10289926","type":"proceedings-article","created":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T17:55:44Z","timestamp":1698861344000},"page":"1330-1334","source":"Crossref","is-referenced-by-count":1,"title":["Improved Disentangled Speech Representations Using Contrastive Learning in Factorized Hierarchical Variational Autoencoder"],"prefix":"10.23919","author":[{"given":"Yuying","family":"Xie","sequence":"first","affiliation":[{"name":"Aalborg University,Department of Electronic Systems,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Arildsen","sequence":"additional","affiliation":[{"name":"Aalborg University,Department of Electronic Systems,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng-Hua","family":"Tan","sequence":"additional","affiliation":[{"name":"Aalborg University,Department of Electronic Systems,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3411495.3421355"},{"key":"ref4","first-page":"4114","article-title":"Challenging common assumptions in the unsupervised learning of disentangled representations","volume-title":"International Conference on Machine Learning","author":"Locatello"},{"key":"ref5","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","author":"Hsu","year":"2017","journal-title":"NIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747625"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747763"},{"key":"ref8","first-page":"5210","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","volume-title":"International Conference on Machine Learning","author":"Qian"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746369"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414487"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747272"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915322"},{"key":"ref16","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"ICLR"},{"key":"ref17","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":"ref18","article-title":"The kaldi speech recognition toolkit","author":"Povey","year":"2011","journal-title":"IEEE Workshop on ASRU"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP52302.2021.9596320"},{"issue":"11","key":"ref20","article-title":"Visualizing data using t-sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of machine learning research"}],"event":{"name":"2023 31st European Signal Processing Conference (EUSIPCO)","location":"Helsinki, Finland","start":{"date-parts":[[2023,9,4]]},"end":{"date-parts":[[2023,9,8]]}},"container-title":["2023 31st European Signal Processing Conference (EUSIPCO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10289698\/10289713\/10289926.pdf?arnumber=10289926","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T10:15:43Z","timestamp":1709374543000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10289926\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,4]]},"references-count":20,"URL":"https:\/\/doi.org\/10.23919\/eusipco58844.2023.10289926","relation":{},"subject":[],"published":{"date-parts":[[2023,9,4]]}}}