{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:31:12Z","timestamp":1730230272968,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683131","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"6540-6544","source":"Crossref","is-referenced-by-count":6,"title":["A Factorial Deep Markov Model for Unsupervised Disentangled Representation Learning from Speech"],"prefix":"10.1109","author":[{"given":"Sameer","family":"Khurana","sequence":"first","affiliation":[]},{"given":"Shafiq Rayhan","family":"Joty","sequence":"additional","affiliation":[]},{"given":"Ahmed","family":"Ali","sequence":"additional","affiliation":[]},{"given":"James","family":"Glass","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Advances in Markov chain Monte Carlo methods","author":"murray","year":"2007","journal-title":"PhD thesis"},{"article-title":"A conceptual introduction to Hamiltonian Monte Carlo","year":"2017","author":"betancourt","key":"ref11"},{"key":"ref12","article-title":"Darpa timit acoustic-phonetic continous speech corpus cd-rom. nist speech disc 1-1.1","volume":"93","author":"garofolo","year":"1993"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268952"},{"key":"ref14","article-title":"Fjord","author":"mcfee","year":"2018","journal-title":"librosa\/librosa 0 6 2"},{"key":"ref15","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref16","article-title":"Support vector machines versus fast scoring in the low-dimensional total variability space for speaker verification","author":"dehak","year":"2009","journal-title":"Tenth Annual Conference of the International Speech Communication Association"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"ref18","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1391"},{"article-title":"Auto-encoding variational bayes","year":"2013","author":"kingma","key":"ref4"},{"article-title":"Unsupervised neural and bayesian models for zero-resource speech processing","year":"2017","author":"kamper","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1034"},{"key":"ref5","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"},{"article-title":"A Deep Generative Model for Disentangled Representations of Sequential Data","year":"2018","author":"li","key":"ref8"},{"key":"ref7","first-page":"2101","article-title":"Structured inference networks for nonlinear state space models","author":"krishnan","year":"2017"},{"key":"ref2","first-page":"40","article-title":"A nonparametric bayesian approach to acoustic model discovery","author":"lee","year":"2012","journal-title":"Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics Long Papers-Volume 1"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSPA.2012.6310546"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1285773"},{"article-title":"Con-volutional neural networks and language embeddings for end-to-end dialect recognition","year":"2018","author":"shon","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639650"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, United Kingdom","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683131.pdf?arnumber=8683131","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:14:24Z","timestamp":1657854864000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683131\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683131","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}