{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:05:57Z","timestamp":1740099957348,"version":"3.37.3"},"reference-count":40,"publisher":"IEEE","funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009950","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383612","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:46:54Z","timestamp":1616705214000},"page":"889-896","source":"Crossref","is-referenced-by-count":3,"title":["Integration of Variational Autoencoder and Spatial Clustering for Adaptive Multi-Channel Neural Speech Separation"],"prefix":"10.1109","author":[{"given":"Katerina","family":"Zmolikova","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Delcroix","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lukas","family":"Burget","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomohiro","family":"Nakatani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan Honza","family":"Cernocky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682623"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8903054"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2018.8516711"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461530"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2284"},{"key":"ref30","article-title":"mir eval: A transparent implementation of common MIR metrics","author":"raffel","year":"2014","journal-title":"Proceedings of the 15th International Society for Music Information Retrieval Conference ISMIR"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2979603"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683704"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659591"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1398"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2912565"},{"article-title":"VAE-DOLPHIN","year":"2020","author":"zmolikova","key":"ref40"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2010.938081"},{"key":"ref12","article-title":"Speech recognition in the presence of highly non-stationary noise based on spatial, spectral and temporal speech\/noise modeling combined with dynamic variance adaptation","author":"delcroix","year":"2011","journal-title":"CHiMEWorkshop on Machine Listening in Multisource Environments"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2008.11.001"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref17","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013","journal-title":"arXiv preprint arXiv 1312 6114"},{"key":"ref18","article-title":"Stochastic backpropagation and approximate inference in deep generative models","author":"rezende","year":"2014","journal-title":"arXiv preprint arXiv 1401 4082"},{"key":"ref19","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":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2025790"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2029711"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref3","first-page":"241","article-title":"Blind speech separation employing directional statistics in an expectation maximization framework","author":"vu","year":"2010","journal-title":"2010 IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref6","article-title":"Chime6 challenge: Tackling multispeaker speech recognition for unsegmented recordings","author":"watanabe","year":"2020","journal-title":"arXiv preprint arXiv 2004 06774"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-552"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-8"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198868"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2277937"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2051355"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952163"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760429"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-15"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/74.3.579"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471664"},{"journal-title":"Pattern Recognition and Machine Learning","year":"2006","author":"bishop","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-721"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461639"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2021,1,19]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383612.pdf?arnumber=9383612","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,31]],"date-time":"2021-05-31T21:31:05Z","timestamp":1622496665000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383612\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383612","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}