{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,29]],"date-time":"2025-03-29T17:57:04Z","timestamp":1743271024317,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/asru.2017.8268989","type":"proceedings-article","created":{"date-parts":[[2018,1,25]],"date-time":"2018-01-25T16:43:53Z","timestamp":1516898633000},"page":"584-590","source":"Crossref","is-referenced-by-count":8,"title":["End-to-end text-independent speaker verification with flexibility in utterance duration"],"prefix":"10.1109","author":[{"given":"Chunlei","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuhito","family":"Koishida","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639154"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2279332"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21236\/ADA613971"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1006\/dspr.1999.0361","article-title":"Speaker verification using adapted gaussian mixture models","volume":"10","author":"a reynolds","year":"2000","journal-title":"Digital Signal Processing"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2006.870086"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.881693"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2544660"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472652"},{"key":"ref19","article-title":"End-to-end attention based text-dependent speaker verification","author":"zhang","year":"2017","journal-title":"IEEE SLT"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472636"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-555"},{"key":"ref6","article-title":"I-vector based physical task stress detection with different fusion strategies","author":"zhang","year":"2015","journal-title":"ISCA INTERSPEECH"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472796"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1159"},{"journal-title":"NIST 2016 speaker recognition evaluation plan","year":"2016","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639151"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1608"},{"key":"ref20","article-title":"Deep neural network based speaker embedding for end-to-end speaker verification","author":"snyder","year":"2016","journal-title":"IEEE SLT"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2016.2647199"},{"key":"ref21","article-title":"TristouNet: Triplet Loss for Speaker Turn Embedding","author":"herv\u00e9","year":"2017","journal-title":"IEEE ICASSP"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref23","first-page":"346","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","author":"he","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref26","first-page":"499","article-title":"A discriminative feature learning approach for deep face recognition","author":"wen","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref25","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"IEEE ASRU"}],"event":{"name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2017,12,16]]},"location":"Okinawa, Japan","end":{"date-parts":[[2017,12,20]]}},"container-title":["2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8260578\/8268903\/08268989.pdf?arnumber=8268989","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,9]],"date-time":"2019-10-09T16:53:13Z","timestamp":1570639993000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8268989\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/asru.2017.8268989","relation":{},"subject":[],"published":{"date-parts":[[2017,12]]}}}