{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T07:45:43Z","timestamp":1768808743440,"version":"3.49.0"},"reference-count":114,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/apsipa.2014.7041826","type":"proceedings-article","created":{"date-parts":[[2015,2,18]],"date-time":"2015-02-18T00:30:35Z","timestamp":1424219435000},"page":"1-10","source":"Crossref","is-referenced-by-count":11,"title":["An overview of robustness related issues in speaker recognition"],"prefix":"10.1109","author":[{"given":"Thomas Fang","family":"Zheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qin","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lantian","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fanhu","family":"Bie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Cold Speech’ for Automatic Speaker Recognition","author":"tull","year":"1996","journal-title":"Acoustical Society of America 131st Meeting Lay Language Papers"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1121\/1.415166"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947593"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"ref31","first-page":"531","article-title":"Probabilistic linear discriminant analysis","author":"ioffe","year":"2006","journal-title":"ECCV"},{"key":"ref30","article-title":"Within-class covariance normalization for SVM-based speaker recognition","author":"hatch","year":"0","journal-title":"INTERSPEECH’ 06 2006"},{"key":"ref37","first-page":"4373","article-title":"Gender-independent speaker recognition using source normalization","author":"mclaren","year":"2012","journal-title":"Proc ICASSP"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288885"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.2001-356","article-title":"Analysis of Speaker Variability","author":"huang","year":"2001"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.859156"},{"key":"ref28","first-page":"1242","article-title":"A straightforward and efficient implementation of the factor analysis model for speaker verification","author":"matrouf","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"ref27","first-page":"57","article-title":"Channel compensation for SVM speaker recognition","author":"solomonoff","year":"2004","journal-title":"Proc Odyssey Speaker and Language Recognition Workshop"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ODYSSEY.2006.248117"},{"key":"ref22","first-page":"495","article-title":"A model-based transformational approach to robust speaker recognition","author":"teunen","year":"2000","journal-title":"Proc ICSLP'00"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596126"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0360"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.881693"},{"key":"ref101","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2008-274","article-title":"Factor analysis subspace estimation for speaker verification with short utterances","author":"vogt","year":"2008","journal-title":"InterSpeech"},{"key":"ref25","first-page":"213","article-title":"Feature warping for robust speaker verification","author":"pelecanos","year":"2001","journal-title":"Proc Speaker Odyssey 2001 conference"},{"key":"ref100","article-title":"Experiments in Speaker Verification using Factor Analysis Likelihood Ratios","author":"kenny","year":"2004","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref50","first-page":"2017","article-title":"Acoustic correlates of task load and stress","author":"scherer","year":"2002","journal-title":"Proc"},{"key":"ref51","first-page":"41","article-title":"Speaker identification in emotional environments","volume":"8","author":"shahin","year":"2009","journal-title":"Iranian Journal of Electrical and Computer Engineering"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479672"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.675367"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ISDA.2012.6416650"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/89.294363"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1976.10155"},{"key":"ref54","first-page":"1","article-title":"Learning polynomial function based neutral-emotion GMM transformation for emotional speaker recognition","author":"shan","year":"0","journal-title":"Proc ICPR-08 2008"},{"key":"ref53","first-page":"2102","article-title":"Study on speaker verification on emotional speech","author":"wu","year":"0","journal-title":"Proc Interspeech 2006"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2013.6694123"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1121\/1.416343"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.08.009"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878256"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1981.1163530"},{"key":"ref5","first-page":"701","article-title":"Recent research in automatic speaker recognition","author":"rosenberg","year":"1992","journal-title":"Advances in Speech Signal Processing"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(99)00080-1"},{"key":"ref49","first-page":"807","article-title":"Can automatic speaker verification be improved by training the algorithms on emotional speech?","author":"scherer","year":"2000","journal-title":"Proc ICSLP'00"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1202292"},{"key":"ref9","year":"0","journal-title":"The NIST Year 2008 Speaker Recognition Evaluation Plan"},{"key":"ref46","first-page":"109","article-title":"Prosody and voice quality in the expression of emotions","author":"zetterholm","year":"0","journal-title":"Proc ICSLP'98 1998 pp"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ChinaSIP.2013.6625304"},{"key":"ref48","first-page":"927","article-title":"Some acoustic characteristics of emotion","author":"pereira","year":"1998","journal-title":"proceedings of ICSLP’96"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/11573548_49"},{"key":"ref42","article-title":"Emotion recognition by speech signals","author":"kwon","year":"0","journal-title":"Proceedings Interspeech 2003"},{"key":"ref41","article-title":"Acoustic analysis of cold-speech: implications for speaker recognition technology and the common cold","author":"tull","year":"1999"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1987.1169544"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/0885-2308(91)90011-E"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366898"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1327105"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415077"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1202764"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1038\/1961253a0"},{"key":"ref77","first-page":"33","article-title":"Person authentication by voice: a need for caution","author":"bonastre","year":"2003","journal-title":"Proc of Eurospeech 2003"},{"key":"ref74","doi-asserted-by":"crossref","first-page":"1","DOI":"10.5120\/11963-7823","article-title":"Combination of Features for Multilingual Speaker Identification with the Constraint of Limited Data","volume":"70","author":"nagaraja","year":"2013","journal-title":"International Journal of Computer Applications"},{"key":"ref75","first-page":"4217","article-title":"The effect of language factors for robust speaker recognition","author":"lu","year":"2009","journal-title":"Acoustics Speech and Signal Processing 2009 ICASSP 2009 IEEE International Conference On IEEE"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1202293"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-49127-9_37"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168412"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1515\/9783110812671"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1515\/text.1.2000.20.1.29"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-4115(08)61535-6"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3115\/991886.991996"},{"key":"ref65","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.2001-417","article-title":"Speaker Recognition based on Idiolectal Differences between Speakers","volume":"4","author":"doddington","year":"2001","journal-title":"Eurospeech"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415078"},{"key":"ref67","article-title":"Duration and Pronunciation Conditioned Lexical Modeling for Speaker Verification","author":"tur","year":"2007","journal-title":"Proc of Interspeech"},{"key":"ref68","article-title":"Gender-dependent Phonetic Refraction For Speaker Recognition","author":"andrews","year":"0","journal-title":"ICASSP 2002"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1202763"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/5.628714"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8655(97)00073-1"},{"key":"ref95","doi-asserted-by":"crossref","first-page":"787","DOI":"10.21437\/Eurospeech.2001-246","article-title":"Speaker recognition in a multi-speaker environment","author":"martin","year":"2001","journal-title":"Proc 7th European Conference on Speech Communication and Technology (Eurospeech 2001)"},{"key":"ref109","first-page":"83","article-title":"Experiments in SVM-based speaker verification using short utterances","author":"mclaren","year":"2010","journal-title":"Proc A Speaker Odyssey&#x2014 Speaker Recognition Workshop"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0359"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ChinaSIP.2013.6625320"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/89.876308"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/MWSCAS.2001.986114"},{"key":"ref92","doi-asserted-by":"crossref","DOI":"10.1201\/9780203166369","article-title":"Forensic Speaker Identification","author":"rose","year":"2002"},{"key":"ref106","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2004-509","article-title":"Robust speaker identification based perceptual log area ratio and Gaussian mixture models","author":"chow","year":"2004","journal-title":"InterSpeech"},{"key":"ref91","article-title":"Speaker Verification: From Research to Reality","author":"reynolds","year":"2001"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref90","article-title":"Spectral Features for Automatic Text-Independent Speaker Recognition","author":"kinnunen","year":"2003"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.04.007"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2006.06.009"},{"key":"ref102","article-title":"Research on Short Utterance Speaker Recognition","author":"zhang","year":"2014"},{"key":"ref111","first-page":"2341","article-title":"i-vector based speaker recognition on short utterances","author":"kanagasundaram","year":"2011","journal-title":"Proceedings of the International Speech Communication Association (INTERSPEECH)"},{"key":"ref112","article-title":"A K-phoneme-class based multi-model method for short utterance speaker recognition","author":"zhang","year":"2012","journal-title":"The 4th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2035786"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2031505"},{"key":"ref99","year":"0","journal-title":"NIST Speaker Recognition Evaluation plans"},{"key":"ref96","article-title":"Robust Speaker Recognition","author":"jin","year":"2007","journal-title":"Carnegie Mellon University"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1983.1172258"},{"key":"ref10","article-title":"The NIST Year 2010 Speaker Recognition Evaluation Plan","year":"0"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1979.1170788"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/89.326616"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1023\/A:1026554814106"},{"key":"ref15","article-title":"Statistical concepts: a second course","author":"lomax","year":"0","journal-title":"Lawrence Erlbaum Associates 2007"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.859163"},{"key":"ref82","first-page":"1","article-title":"Effects of time lapse on speaker recognition results","author":"beigi","year":"2009","journal-title":"Proc of 16th International Conference on Digital Signal Processing"},{"key":"ref17","first-page":"352","article-title":"Robust continuous speech recognition using parallel model combination","author":"mark","year":"1996","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163201"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.862086"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(99)00075-8"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367163"},{"key":"ref83","article-title":"Fundamentals of speaker recognition","author":"beigi","year":"2010","journal-title":"New York Springer"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CCST.2008.4751310"},{"key":"ref113","doi-asserted-by":"crossref","DOI":"10.21437\/ICSLP.1998-242","article-title":"Multilateral techniques for speaker recognition","author":"parris","year":"1998","journal-title":"International Conference on Spoken Language Processing (ICSLP)"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1155\/S1110865704310024"},{"key":"ref89","article-title":"Automatic Speaker Recognition Using Gaussian Mixture Speaker Models","author":"reynolds","year":"0","journal-title":"The Lincoln Laboratory Journal 1995"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19530-3_11"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICB.2012.6199796"},{"key":"ref87","article-title":"An Investigation into Better Frequency Warping for Time-Varying Sneaker Recognition","author":"wang","year":"0","journal-title":"APSTPA ASC 2012"},{"key":"ref88","article-title":"Creation of time-varying voiceprint database","author":"wang","year":"2010","journal-title":"Proceedings of COCOSDA 2010"}],"event":{"name":"2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","location":"Chiang Mai, Thailand","start":{"date-parts":[[2014,12,9]]},"end":{"date-parts":[[2014,12,12]]}},"container-title":["Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7016284\/7041492\/07041826.pdf?arnumber=7041826","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,6]],"date-time":"2023-08-06T06:27:45Z","timestamp":1691303265000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7041826\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":114,"URL":"https:\/\/doi.org\/10.1109\/apsipa.2014.7041826","relation":{},"subject":[],"published":{"date-parts":[[2014,12]]}}}