{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:39:14Z","timestamp":1730230754513,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054595","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T16:21:13Z","timestamp":1586449273000},"page":"6774-6778","source":"Crossref","is-referenced-by-count":2,"title":["Mixture Factorized Auto-Encoder for Unsupervised Hierarchical Deep Factorization of Speech Signal"],"prefix":"10.1109","author":[{"given":"Zhiyuan","family":"Peng","sequence":"first","affiliation":[]},{"given":"Siyuan","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Tan","family":"Lee","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Understanding posterior collapse in generative latent variable models","volume":"2019","author":"lucas","year":"2019","journal-title":"Deep Generative Models for Highly Structured Data ICLR 2019 Workshop"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"article-title":"Auto-encoding variational bayes","year":"0","author":"kingma","key":"ref12"},{"key":"ref13","first-page":"710","article-title":"Learning disentangled joint continuous and discrete representations","author":"dupont","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2486"},{"key":"ref15","first-page":"3086","article-title":"A? sampling","author":"maddison","year":"2014","journal-title":"Advances in Neural Information Processing Systems 27"},{"key":"ref16","article-title":"Categorical reparameterization with gumbel-softmax","volume":"2017","author":"jang","year":"2017","journal-title":"5th International Conference on Learning Representations - ICLR 2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"Voxceleb: a large-scale speaker identification dataset","author":"nagrani","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-44415-3_47"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2496226"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"999","DOI":"10.21437\/Interspeech.2017-620","article-title":"Deep neural network embeddings for text-independent speaker verification","author":"snyder","year":"2017","journal-title":"InterSpeech"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1226"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462169"},{"key":"ref8","first-page":"5656","article-title":"Disentangled sequential autoencoder","volume":"2018","author":"li","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning ICML 2018"},{"key":"ref7","first-page":"1878","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","author":"hsu","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2360798"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2842"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-15"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1109\/ASRU.2017.8268953","article-title":"The zero resource speech challenge 2017","author":"dunbar","year":"2017","journal-title":"Automatic Speech Recognition and Understanding (ASRU) 2017 IEEE Workshop on"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054595.pdf?arnumber=9054595","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:08:58Z","timestamp":1656360538000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054595\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054595","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}