{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:25:00Z","timestamp":1775229900665,"version":"3.50.1"},"reference-count":26,"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\/icassp39728.2021.9414487","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"3860-3864","source":"Crossref","is-referenced-by-count":11,"title":["Contrastive Predictive Coding Supported Factorized Variational Autoencoder For Unsupervised Learning Of Disentangled Speech Representations"],"prefix":"10.1109","author":[{"given":"Janek","family":"Ebbers","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Kuhlmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tobias","family":"Cord-Landwehr","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Reinhold","family":"Haeb-Umbach","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2917232"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1830"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682589"},{"key":"ref13","article-title":"Voice conversion using cycle-consistent variational autoencoder with multiple decoders","author":"lee","year":"2019","journal-title":"arXiv preprint arXiv 1909 01771"},{"key":"ref14","first-page":"1878","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","author":"hsu","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053854"},{"key":"ref17","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":"ref18","article-title":"Unsupervised speech decomposition via triple information bottleneck","author":"qian","year":"2020","journal-title":"arXiv preprint arXiv 2004 10491"},{"key":"ref19","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"2nd International Conference on Learning Representations ICLR 2014"},{"key":"ref4","first-page":"2610","article-title":"Isolating sources of disentanglement in variational autoencoders","author":"chen","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref3","first-page":"2649","article-title":"Disentangling by factorising","author":"kim","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref6","first-page":"5967","article-title":"Fader networks: Manipulating images by sliding attributes","author":"lample","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref5","article-title":"dSprites: Disentanglement testing sprites dataset","author":"matthey","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00087"},{"key":"ref2","first-page":"6","article-title":"beta-VAE: Learning basic visual concepts with a constrained variational framework","volume":"2","author":"higgins","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"ref9","first-page":"6306","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref1","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"arXiv preprint arXiv 1807 03748"},{"key":"ref20","article-title":"Vocal tract length perturbation (vtlp) improves speech recognition","volume":"117","author":"jaitly","year":"2013","journal-title":"Proceedings of ICML Workshop on Deep Learning for Audio Speech and Language"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref21","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"ulyanov","year":"2016","journal-title":"arXiv preprint arXiv 1607 08022"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref25","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"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\/09414487.pdf?arnumber=9414487","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:00Z","timestamp":1652197260000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414487\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414487","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}