{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,8,15]],"date-time":"2023-08-15T07:10:24Z","timestamp":1692083424713},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2015,10,12]],"date-time":"2015-10-12T00:00:00Z","timestamp":1444608000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"The RGC of Hong Kong","award":["PolyU 152117\/14E"],"award-info":[{"award-number":["PolyU 152117\/14E"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1007\/s10772-015-9310-8","type":"journal-article","created":{"date-parts":[[2015,10,13]],"date-time":"2015-10-13T06:10:16Z","timestamp":1444716616000},"page":"633-648","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Noise robust speaker verification via the fusion of SNR-independent and SNR-dependent PLDA"],"prefix":"10.1007","volume":"18","author":[{"given":"Xiaomin","family":"Pang","sequence":"first","affiliation":[]},{"given":"Man-Wai","family":"Mak","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,10,12]]},"reference":[{"key":"9310_CR1","volume-title":"Pattern recognition and machine learning","author":"C Bishop","year":"2006","unstructured":"Bishop, C. (2006). Pattern recognition and machine learning. New York: Springer."},{"key":"9310_CR2","unstructured":"Br\u00fcmmer, N. (2014). FoCal. https:\/\/www.sitesgooglecom\/site\/nikobrummer\/focal ."},{"key":"9310_CR3","unstructured":"Br\u00fcmmer, N., & de Villiers, E. (2011). The Bosaris toolkit user guide: Theory, algorithms and code for binary classifier score processing. Documentation of Bosaris toolkit. https:\/\/sites.google.com\/site\/bosaristoolkit\/"},{"issue":"4","key":"9310_CR4","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2011","unstructured":"Dehak, N., Kenny, P., Dehak, R., Dumouchel, P., & Ouellet, P. (2011). Front-end factor analysis for speaker verification. IEEE Transactions on Audio, Speech, and Language Processing, 19(4), 788\u2013798.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9310_CR5","unstructured":"Ferrer, L., Bratt, H., Burget, L., Cernocky, H., Glembek, O., Graciarena, M., et al. (2011). Promoting robustness for speaker modeling in the community: The PRISM evaluation set. In Proceedings of NIST 2011 workshop."},{"key":"9310_CR6","doi-asserted-by":"crossref","unstructured":"Garcia-Romero, D., & Espy-Wilson, C. (2011). Analysis of i-vector length normalization in speaker recognition systems. In Proceedings of interspeech (pp. 249\u2013252).","DOI":"10.21437\/Interspeech.2011-53"},{"key":"9310_CR7","doi-asserted-by":"crossref","unstructured":"Garcia-Romero, D., Zhou, X., & Espy-Wilson, C. (2012). Multicondition training of Gaussian PLDA models in i-vector space for noise and reverberation robust speaker recognition. In 2012 IEEE international conference on acoustics, speech and signal processing (ICASSP, pp. 4257\u20134260).","DOI":"10.1109\/ICASSP.2012.6288859"},{"issue":"4","key":"9310_CR8","doi-asserted-by":"crossref","first-page":"842","DOI":"10.1109\/TASL.2012.2226161","volume":"21","author":"T Hasan","year":"2013","unstructured":"Hasan, T., & Hansen, J. (2013). Acoustic factor analysis for robust speaker verification. IEEE Transactions on Audio, Speech, and Language Processing, 21(4), 842\u2013853.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"2","key":"9310_CR9","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1109\/TASLP.2013.2292356","volume":"22","author":"T Hasan","year":"2014","unstructured":"Hasan, T., & Hansen, J. (2014). Maximum likelihood acoustic factor analysis models for robust speaker verification in noise. IEEE Transactions on Audio, Speech, and Language Processing, 22(2), 381\u2013391.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9310_CR10","doi-asserted-by":"crossref","unstructured":"Hasan, T., Sadjadi, S. O., Liu, G., Shokouhi, N., Boril, H., & Hansen, J. H. L. (2013). CRSS system for 2012 NIST speaker recognition evaluation. In 2013 IEEE international conference on acoustics, speech and signal processing (ICASSP, pp. 6783\u20136787).","DOI":"10.1109\/ICASSP.2013.6638975"},{"key":"9310_CR11","doi-asserted-by":"crossref","unstructured":"Hatch, A., Kajarekar, S., & Stolcke, A. (2006). Within-class covariance normalization for SVM-based speaker recognition. In Proceedings of the 9th international conference on spoken language processing, Pittsburgh, PA, USA (pp. 1471\u20131474).","DOI":"10.21437\/Interspeech.2006-183"},{"key":"9310_CR12","unstructured":"Kenny, P. (2010). Bayesian speaker verification with heavy-tailed priors. In Proceedings of Odyssey. 2010 Speaker and language recognition workshop. Brno: Czech Republic."},{"issue":"4","key":"9310_CR13","doi-asserted-by":"crossref","first-page":"1435","DOI":"10.1109\/TASL.2006.881693","volume":"15","author":"P Kenny","year":"2007","unstructured":"Kenny, P., Boulianne, G., Ouellet, P., & Dumouchel, P. (2007). Joint factor analysis versus eigenchannels in speaker recognition. IEEE Transactions on Audio, Speech and Language Processing, 15(4), 1435\u20131447.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"5","key":"9310_CR14","doi-asserted-by":"crossref","first-page":"980","DOI":"10.1109\/TASL.2008.925147","volume":"16","author":"P Kenny","year":"2008","unstructured":"Kenny, P., Ouellet, P., Dehak, N., Gupta, V., & Dumouchel, P. (2008). A study of inter-speaker variability in speaker verification. IEEE Transactions on Audio, Speech and Language Processing, 16(5), 980\u2013988.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"9310_CR15","doi-asserted-by":"crossref","unstructured":"Leeuwen, D. A., & Saeidi, R. (2013). Knowing the non-target speakers: The effect of the i-vector population for PLDA training in speaker recognition. In 2013 IEEE international conference on acoustics, speech and signal processing (ICASSP), Vancouver, BC, Canada (pp. 6778\u20136782).","DOI":"10.1109\/ICASSP.2013.6638974"},{"key":"9310_CR16","doi-asserted-by":"crossref","unstructured":"Lei, Y., Burget, L., Ferrer, L., Graciarena, M., & Scheffer, N. (2012). Towards noise-robust speaker recognition using probabilistic linear discriminant analysis. In 2012 IEEE international conference on acoustics, speech and signal processing (ICASSP), Kyoto, Japan (pp. 4253\u20134256).","DOI":"10.1109\/ICASSP.2012.6288858"},{"key":"9310_CR17","doi-asserted-by":"crossref","unstructured":"Lei, Y., Burget, L., & Scheffer, N. (2013). A noise robust i-vector extractor using vector Taylor series for speaker recognition. In 2013 IEEE international conference on acoustics, speech and signal processing (ICASSP, pp. 6788\u20136791).","DOI":"10.1109\/ICASSP.2013.6638976"},{"key":"9310_CR18","doi-asserted-by":"crossref","unstructured":"Lei, Y., Mclaren, M., Ferrer, L., & Scheffer, N. (2014). Simplified VTS-based i-vector extraction in noise-robust speaker recognition. In 2014 IEEE international conference on acoustics, speech and signal processing (ICASSP, pp. 4065\u20134069).","DOI":"10.1109\/ICASSP.2014.6854360"},{"key":"9310_CR19","doi-asserted-by":"crossref","unstructured":"Li, Q., & Huang, Y. (2010). Robust speaker identification using an auditory-based feature. In 2010 IEEE international conference on acoustics, speech and signal processing (ICASSP, pp. 4514\u20134517).","DOI":"10.1109\/ICASSP.2010.5495589"},{"issue":"1","key":"9310_CR20","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1016\/j.csl.2013.07.003","volume":"28","author":"MW Mak","year":"2013","unstructured":"Mak, M. W., & Yu, H. B. (2013). A study of voice activity detection techniques for NIST speaker recognition evaluations. Computer, Speech and Language, 28(1), 295\u2013313.","journal-title":"Computer, Speech and Language"},{"key":"9310_CR21","doi-asserted-by":"crossref","unstructured":"Mallidi, S., Ganapathy, S., & Hermansky, H. (2013). Robust speaker recognition using spectro-temporal autoregressive models. In Proceedings of interspeech.","DOI":"10.21437\/Interspeech.2013-692"},{"key":"9310_CR22","doi-asserted-by":"crossref","unstructured":"Martin, A., Doddington, G., Kamm, T., Ordowski, M., & Przybocki, M. (1997). The DET curve in assessment of detection task performance. In Proceedings of Eurospeech\u201997 (pp. 1895\u20131898).","DOI":"10.21437\/Eurospeech.1997-504"},{"key":"9310_CR23","doi-asserted-by":"crossref","unstructured":"Martinez, D., Burget, L., Stafylakis, T., Lei, Y., Kenny, P., & Lleida, E. (2014). Unscented transform for i-vector-based noisy speaker recognition. In 2014 IEEE international conference on acoustics, speech and signal processing (ICASSP, pp. 4070\u20134074).","DOI":"10.1109\/ICASSP.2014.6854361"},{"key":"9310_CR24","unstructured":"McLaren, M., Mandasari, M., & Leeuwen, D. (2012). Source normalization for language-independent speaker recognition using i-vectors. In Proceedings of Odyssey 2012: The speaker and language recognition workshop (pp. 55\u201361)."},{"key":"9310_CR25","doi-asserted-by":"crossref","unstructured":"McLaren, M., Scheffer, N., Graciarena, M., Ferrer, L., & Lei, Y. (2013). Improving speaker identification robustness to highly channel-degraded speech through multiple system fusion. In 2013 IEEE international conference on acoustics, speech and signal processing (ICASSP, pp. 6773\u20136777).","DOI":"10.1109\/ICASSP.2013.6638973"},{"issue":"5","key":"9310_CR26","doi-asserted-by":"crossref","first-page":"1711","DOI":"10.1109\/TASL.2007.899278","volume":"15","author":"J Ming","year":"2007","unstructured":"Ming, J., Hazen, T., Glass, J., & Reynolds, D. (2007). Robust speaker recognition in noisy conditions. IEEE Transactions on Audio, Speech and Language Processing, 15(5), 1711\u20131723.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"4","key":"9310_CR27","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1007\/BF02108643","volume":"2","author":"SFDC Neto","year":"1999","unstructured":"Neto, S. F. D. C. (1999). The ITU-T software tool library. International Journal of Speech Technology, 2(4), 259\u2013272.","journal-title":"International Journal of Speech Technology"},{"key":"9310_CR28","unstructured":"NIST. (2012). The NIST year 2012 speaker recognition evaluation plan. http:\/\/www.nistgov\/itl\/iad\/mig\/sre12cfm ."},{"key":"9310_CR29","doi-asserted-by":"crossref","unstructured":"Pang, X. M., & Mak, M. W. (2014). Fusion of SNR-dependent PLDA models for noise robust speaker verification. In ISCSLP\u20192014 (pp. 619\u2013623).","DOI":"10.1109\/ISCSLP.2014.6936593"},{"key":"9310_CR30","unstructured":"Pelecanos, J., & Sridharan, S. (2001). Feature warping for robust speaker verification. In Proceedings of Odyssey, 2001. The speaker and language recognition workshop, Crete, Greece (pp. 213\u2013218)."},{"key":"9310_CR31","doi-asserted-by":"crossref","unstructured":"Prince, S., & Elder, J. (2007). Probabilistic linear discriminant analysis for inferences about identity. In IEEE 11th international conference on computer vision, 2007 (ICCV 2007, pp. 1\u20138).","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"9310_CR32","doi-asserted-by":"crossref","unstructured":"Rajan, P., Afanasyev, A., Hautam\u00e4ki, V., & Kinnunen, T. (2014). From single to multiple enrollment i-vectors: Practical PLDA scoring variants for speaker verification. Digital Signal Processing Online. doi: 10.1016\/j.dsp.2014.05.001 .","DOI":"10.1016\/j.dsp.2014.05.001"},{"key":"9310_CR33","doi-asserted-by":"crossref","unstructured":"Rajan, P., Kinnunen, T., & Hautam\u00e4ki, V. (2013). Effect of multicondition training on i-vector PLDA configurations for speaker recognition. In Proceedings of interspeech (pp. 3694\u20133697).","DOI":"10.21437\/Interspeech.2013-693"},{"issue":"5","key":"9310_CR34","doi-asserted-by":"crossref","first-page":"1012","DOI":"10.1109\/TASL.2013.2243436","volume":"21","author":"W Rao","year":"2013","unstructured":"Rao, W., & Mak, M. W. (2013). Boosting the performance of i-vector based speaker verification via utterance partitioning. IEEE Transactions on Audio, Speech and Language Processing, 21(5), 1012\u20131022.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"1\u20133","key":"9310_CR35","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1006\/dspr.1999.0361","volume":"10","author":"DA Reynolds","year":"2000","unstructured":"Reynolds, D. A., Quatieri, T. F., & Dunn, R. B. (2000). Speaker verification using adapted Gaussian mixture models. Digital Signal Processing, 10(1\u20133), 19\u201341.","journal-title":"Digital Signal Processing"},{"key":"9310_CR36","doi-asserted-by":"crossref","unstructured":"Sadjadi, S. O., Hasan, T., & Hansen, J. (2012). Mean Hilbert envelope coefficients (MHEC) for robust speaker recognition. In Proceedings of interspeech (pp. 1696\u20131699).","DOI":"10.21437\/Interspeech.2012-464"},{"key":"9310_CR37","doi-asserted-by":"crossref","unstructured":"Sadjadi, S., Pelecanos, J., & Zhu, W. (2014). Nearest neighbor discriminant analysis for robust speaker recognition. In Proceedings of interspeech (pp. 1860\u20131864).","DOI":"10.21437\/Interspeech.2014-422"},{"key":"9310_CR38","unstructured":"Saeidi, R., & van Leeuwen, D. A. (2012). The Radboud University Nijmegen submission to NIST SRE-2012. In Proceedings of the NIST speaker recognition evaluation workshop."},{"key":"9310_CR39","doi-asserted-by":"crossref","unstructured":"Shao, Y., & Wang, D. (2008). Robust speaker identification using auditory features and computational auditory scene analysis. In 2008 IEEE international conference on acoustics, speech and signal processing (ICASSP, pp. 1589\u20131592).","DOI":"10.1109\/ICASSP.2008.4517928"},{"key":"9310_CR40","doi-asserted-by":"crossref","unstructured":"Yu, C., Liu, G., Hahm, S., & Hansen, J. (2014). Uncertainty propagation in front end factor analysis for noise robust speaker recognition. In 2014 IEEE international conference on acoustics, speech and signal processing (ICASSP, pp. 4045\u20134049).","DOI":"10.1109\/ICASSP.2014.6854356"},{"key":"9310_CR41","doi-asserted-by":"crossref","unstructured":"Yu, H., & Mak, M. (2011). Comparison of voice activity detectors for interview speech in NIST speaker recognition evaluation. In Proceedings of interspeech (pp. 2353\u20132356).","DOI":"10.21437\/Interspeech.2011-61"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-015-9310-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-015-9310-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-015-9310-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,15]],"date-time":"2023-08-15T06:28:11Z","timestamp":1692080891000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-015-9310-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,10,12]]},"references-count":41,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2015,12]]}},"alternative-id":["9310"],"URL":"https:\/\/doi.org\/10.1007\/s10772-015-9310-8","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,10,12]]}}}