{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T16:03:05Z","timestamp":1730304185798,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,22]],"date-time":"2023-10-22T00:00:00Z","timestamp":1697932800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,22]],"date-time":"2023-10-22T00:00:00Z","timestamp":1697932800000},"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":[[2023,10,22]]},"DOI":"10.1109\/waspaa58266.2023.10248146","type":"proceedings-article","created":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T17:31:37Z","timestamp":1694799097000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Directional Target Speaker Extraction under Noisy Underdetermined Conditions through Conditional Variational Autoencoder with Global Style Tokens"],"prefix":"10.1109","author":[{"given":"Rui","family":"Wang","sequence":"first","affiliation":[{"name":"Nagoya University,Graduate School of Informatics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Nagoya University,Information Technology Center"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.3000199"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2577880"},{"key":"ref15","first-page":"13","article-title":"Experimental evaluation of multichannel audio source separation based on IDLMA","volume":"117","author":"kitamura","year":"2018","journal-title":"IEICE Tech Rep"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2580946"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/11679363_21"},{"key":"ref10","first-page":"846","article-title":"Geometrically constrained independent vector analysis for directional speech enhancement","author":"li","year":"2020","journal-title":"Proc ICASSP"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref17","first-page":"3581","article-title":"Semi-supervised learning with deep generative models","author":"kingma","year":"2014","journal-title":"Adv NIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01217"},{"key":"ref19","first-page":"5167","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"Proc ICML"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9979881"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1186\/1687-6180-2014-26"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TAP.1986.1143832"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462657"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2011.6082320"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2005.1540173"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.803443"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-00599-2_97"},{"key":"ref28","article-title":"DEMAND: a collection of multi-channel recordings of acoustic noise in diverse environments","author":"thiemann","year":"2013","journal-title":"Supported by Inria under the Associate Team Program VERSAMUS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-73031-8_10"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2319155"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_46"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.803443"},{"article-title":"New insights on target speaker extraction","year":"2022","author":"elminshawi","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960271"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876730"}],"event":{"name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","start":{"date-parts":[[2023,10,22]]},"location":"New Paltz, NY, USA","end":{"date-parts":[[2023,10,25]]}},"container-title":["2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10248019\/10248047\/10248146.pdf?arnumber=10248146","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T17:40:59Z","timestamp":1696268459000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10248146\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,22]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/waspaa58266.2023.10248146","relation":{},"subject":[],"published":{"date-parts":[[2023,10,22]]}}}