{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T10:25:32Z","timestamp":1760955932360,"version":"3.41.2"},"reference-count":25,"publisher":"IEEE","license":[{"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.2019.8683881","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"6001-6005","source":"Crossref","is-referenced-by-count":3,"title":["Analysis and Mitigation of Vocal Effort Variations in Speaker Recognition"],"prefix":"10.1109","author":[{"given":"Mahesh Kumar","family":"Nandwana","sequence":"first","affiliation":[{"name":"Speech Technology and Research Laboratory, SRI International, Menlo Park, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mitchell","family":"McLaren","sequence":"additional","affiliation":[{"name":"Speech Technology and Research Laboratory, SRI International, Menlo Park, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luciana","family":"Ferrer","sequence":"additional","affiliation":[{"name":"Instituto de Investigacón en Ciencias de la Computación, UBA-CONICET, Argentina"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diego","family":"Castan","sequence":"additional","affiliation":[{"name":"Speech Technology and Research Laboratory, SRI International, Menlo Park, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aaron","family":"Lawson","sequence":"additional","affiliation":[{"name":"Speech Technology and Research Laboratory, SRI International, Menlo Park, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2091631"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2493366"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2009019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846266"},{"key":"ref14","first-page":"327","article-title":"How to train your speaker embeddings extractor","author":"mclaren","year":"2018","journal-title":"Odyssey 2018"},{"key":"ref15","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":"Proc Interspeech 2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1102"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"249","DOI":"10.21437\/Interspeech.2011-53","article-title":"Analysis of i-vector length normalization in speaker recognition systems","author":"garcia-romero","year":"2011","journal-title":"Interspeech 2011"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1121\/1.4979337"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"1982","DOI":"10.21437\/Interspeech.2015-436","article-title":"A new front-end for classification of non-speech sounds: a study on human whistle","author":"nandwana","year":"2015","journal-title":"Proceedings of Interspeech 2015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2221"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.09.004"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2015.2462851"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"3698","DOI":"10.21437\/Interspeech.2013-694","article-title":"Improving robustness to compressed speech in speaker recognition","author":"mclaren","year":"2013","journal-title":"INTERSPEECH-2013"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"2253","DOI":"10.21437\/Interspeech.2014-249","article-title":"Analysis and identification of human scream: implications for speaker recognition","author":"nandwana","year":"2014","journal-title":"Proc INTERSPEECH 2014"},{"key":"ref9","first-page":"747","article-title":"The influence of vocal effort on human speaker identification","author":"brungart","year":"2001","journal-title":"EUROSPEECH-2001"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"609","DOI":"10.21437\/Interspeech.2008-195","article-title":"Effects of vocal effort and speaking style on text-independent speaker verification","author":"shriberg","year":"2008","journal-title":"INTERSPEECH-2008"},{"key":"ref20","article-title":"Promoting robustness for speaker modeling in the community: the PRISM evaluation set","author":"ferrer","year":"2011","journal-title":"Proceedings of NIST 2011 Workshop"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"1855","DOI":"10.21437\/Interspeech.2014-421","article-title":"SNR-dependent mixture of PLDA for noise robust speaker verification","author":"mak","year":"2014","journal-title":"Proc INTERSPEECH 2014"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2005.08.001"},{"key":"ref24","first-page":"317","article-title":"A unified approach for audio characterization and its application to speaker recognition","author":"ferrer","year":"2012","journal-title":"Odyssey 2012"},{"key":"ref23","first-page":"19","article-title":"Trial-Based Calibration for speaker recognition in unseen conditions","author":"mclaren","year":"2014","journal-title":"Odyssey 2014"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2875794"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, UK","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\/08683881.pdf?arnumber=8683881","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T19:33:42Z","timestamp":1753731222000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683881\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683881","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}