{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T13:51:13Z","timestamp":1762782673152,"version":"3.37.3"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,25]],"date-time":"2021-10-25T00:00:00Z","timestamp":1635120000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,25]],"date-time":"2021-10-25T00:00:00Z","timestamp":1635120000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,25]],"date-time":"2021-10-25T00:00:00Z","timestamp":1635120000000},"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":[[2021,10,25]]},"DOI":"10.1109\/mlsp52302.2021.9596320","type":"proceedings-article","created":{"date-parts":[[2021,11,15]],"date-time":"2021-11-15T22:53:58Z","timestamp":1637016838000},"page":"1-6","source":"Crossref","is-referenced-by-count":10,"title":["Disentangled Speech Representation Learning Based on Factorized Hierarchical Variational Autoencoder with Self-Supervised Objective"],"prefix":"10.1109","author":[{"given":"Yuying","family":"Xie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Arildsen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng-Hua","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054438"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3055180"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414487"},{"key":"ref15","first-page":"27403","article-title":"Darpa timit acoustic-phonetic continous speech corpus cd-rom. nist speech disc 1-1.1","volume":"93","author":"garofolo","year":"1993","journal-title":"NASA STI\/Recon Technical Report N"},{"key":"ref16","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"IEEE Workshop on ASRU"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404779"},{"journal-title":"Speaker de-identification using a factorized hierarchical variational autoencoder","year":"2018","author":"kastbjerg","key":"ref18"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10340","article-title":"Joint word representation learning using a corpus and a semantic lexicon","author":"bollegala","year":"2016","journal-title":"AAAI"},{"key":"ref3","article-title":"Robust graph representation learning via neural sparsification","author":"zheng","year":"2020","journal-title":"ICML"},{"key":"ref6","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","author":"hsu","year":"2017","journal-title":"NIPS"},{"key":"ref5","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"ICLRE"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054534"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-15"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053571"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref9","article-title":"Singing voice conversion with disentangled representations of singer and vocal technique using variational autoen-coders","author":"luo","year":"2020","journal-title":"ICASSP"}],"event":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","start":{"date-parts":[[2021,10,25]]},"location":"Gold Coast, Australia","end":{"date-parts":[[2021,10,28]]}},"container-title":["2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9596063\/9596068\/09596320.pdf?arnumber=9596320","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,12]],"date-time":"2023-11-12T17:37:42Z","timestamp":1699810662000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9596320\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,25]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/mlsp52302.2021.9596320","relation":{},"subject":[],"published":{"date-parts":[[2021,10,25]]}}}