{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:36:49Z","timestamp":1760132209902},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2012,6,15]],"date-time":"2012-06-15T00:00:00Z","timestamp":1339718400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2012,9]]},"DOI":"10.1007\/s10772-012-9149-1","type":"journal-article","created":{"date-parts":[[2012,6,18]],"date-time":"2012-06-18T14:41:44Z","timestamp":1340030504000},"page":"351-364","source":"Crossref","is-referenced-by-count":1,"title":["Multiple background models for speaker verification using the concept of vocal tract length and MLLR super-vector"],"prefix":"10.1007","volume":"15","author":[{"given":"A. K.","family":"Sarkar","sequence":"first","affiliation":[]},{"given":"S.","family":"Umesh","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2012,6,15]]},"reference":[{"key":"9149_CR1","doi-asserted-by":"crossref","first-page":"1713","DOI":"10.21437\/Interspeech.2008-382","volume-title":"Proc. of interspeech","author":"P. T. Akhil","year":"2008","unstructured":"Akhil, P. T., Rath, S. P., Umesh, S., & Sanand, D. R. (2008). A computationally efficient approach to warp factor estimation in VTLN using EM algorithm and sufficient statistics. In Proc. of interspeech (pp. 1713\u20131716)."},{"key":"9149_CR2","doi-asserted-by":"crossref","first-page":"1379","DOI":"10.21437\/Eurospeech.1997-343","volume-title":"Proc. of Eur. conf. speech commun. and tech. (Eurospeech)","author":"A. M. Ariyaeeinia","year":"1997","unstructured":"Ariyaeeinia, A. M., & Sivakumaran, P. (1997). Analysis and comparison of score normalization methods for text dependent speaker verification. In Proc. of Eur. conf. speech commun. and tech. (Eurospeech) (pp. 1379\u20131382)."},{"key":"9149_CR3","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1006\/dspr.1999.0360","volume":"10","author":"R. Auckenthaler","year":"2000","unstructured":"Auckenthaler, R., Carey, M., & Lloyd-Thomas, H. (2000). Score normalization for text-independent speaker verification system. Digital Signal Processing, 10, 42\u201354.","journal-title":"Digital Signal Processing"},{"key":"9149_CR4","doi-asserted-by":"crossref","first-page":"1271","DOI":"10.21437\/Interspeech.2009-379","volume-title":"Proc. of interspeech","author":"Y. Bar-Yosef","year":"2009","unstructured":"Bar-Yosef, Y., & Bistritz, Y. (2009). Adaptive individual background model for speaker verification. In Proc. of interspeech (pp. 1271\u20131274)."},{"key":"9149_CR5","volume-title":"Proc. of NIST 2004 speaker recognition workshop","author":"J. F. Bonastre","year":"2004","unstructured":"Bonastre, J. F., Scheffer, N., Fredouille, C., & Matrouf, D. (2004). Nist\u201904 speaker recognition evaluation campaign: new LIA speaker detection plateform based on ALIZE toolkit. In Proc. of NIST 2004 speaker recognition workshop."},{"key":"9149_CR6","first-page":"97","volume-title":"Proc. of IEEE int. conf. acoust. speech signal processing (ICASSP)","author":"W. Campbell","year":"2006","unstructured":"Campbell, W., Sturim, D., Reynolds, D., & Solomonoff, A. (2006). SVM based speaker verification using a GMM supervector kernel and NAP variability compensation. In Proc. of IEEE int. conf. acoust. speech signal processing (ICASSP) (pp. 97\u2013100)."},{"key":"9149_CR7","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.patrec.2006.06.008","volume":"28","author":"D. R. Castro","year":"2007","unstructured":"Castro, D. R., et al. (2007). Speaker verification using speaker- and test-dependent fast score normalization. Pattern Recognition Letters, 28, 90\u201398.","journal-title":"Pattern Recognition Letters"},{"key":"9149_CR8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"A. Dempster","year":"1977","unstructured":"Dempster, A., Laird, N., & Rubin, D. (1977). Maximum likelihood from incomplete data via EM algorithm. Journal of the Royal Statistical Society, 39, 1\u201338.","journal-title":"Journal of the Royal Statistical Society"},{"key":"9149_CR9","first-page":"53","volume-title":"Proc. of IEEE int. conf. acoust. speech signal processing (ICASSP)","author":"M. Ferras","year":"2007","unstructured":"Ferras, M., Leung, C. C., Barras, C., & Gauvain, J. L. (2007). Constrained MLLR for speaker recognition. In Proc. of IEEE int. conf. acoust. speech signal processing (ICASSP) (pp. 53\u201356)."},{"key":"9149_CR10","doi-asserted-by":"crossref","first-page":"1985","DOI":"10.21437\/Interspeech.2005-624","volume-title":"Proc. of interspeech","author":"J. Goldberger","year":"2005","unstructured":"Goldberger, J., & Aronowitz, H. (2005). A distance measure between GMMs based on the unscented transform and its application to speaker recognition. In Proc. of interspeech (pp. 1985\u20131989)."},{"key":"9149_CR11","first-page":"841","volume-title":"Proc. of IEEE int. conf. acoust. speech signal processing (ICASSP)","author":"T. Isobe","year":"1999","unstructured":"Isobe, T., & Takahashi, J. (1999). A new cohort normalization using local acoustic information for speaker verification. In Proc. of IEEE int. conf. acoust. speech signal processing (ICASSP) (pp. 841\u2013844)."},{"key":"9149_CR12","unstructured":"Kenny, P. (2006). Joint factor analysis of speaker and session variability: theory and algorithms (Technical report CRIM-06\/08-13). Montreal, CRIM."},{"key":"9149_CR13","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1109\/89.650310","volume":"6","author":"L. Lee","year":"1998","unstructured":"Lee, L., & Rose, R. (1998). Frequency warping approach to speaker normalization. IEEE Transactions on Speech and Audio Processing, 6, 49\u201359.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9149_CR14","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1006\/csla.1995.0010","volume":"9","author":"C. Leggetter","year":"1995","unstructured":"Leggetter, C., & Woodland, P. (1995). Maximum likelihood linear regression for speaker adaptation of Hmms. Computer Speech & Language, 9, 171\u2013186.","journal-title":"Computer Speech & Language"},{"key":"9149_CR15","doi-asserted-by":"crossref","first-page":"1895","DOI":"10.21437\/Eurospeech.1997-504","volume-title":"Proc. of Eur. conf. speech commun. and tech, Eurospeech","author":"A. Martin","year":"1997","unstructured":"Martin, A., Doddington, G., Kamm, T., Ordowskiand, M., & Przybocki, M. (1997). The det curve in assessment of detection task performance. In Proc. of Eur. conf. speech commun. and tech, Eurospeech (pp. 1895\u20131898)."},{"key":"9149_CR16","doi-asserted-by":"crossref","first-page":"3109","DOI":"10.21437\/Interspeech.2005-668","volume-title":"Proc. of interspeech","author":"M. Mason","year":"2005","unstructured":"Mason, M., Vogt, R., Baker, B., & Sridharan, S. (2005). Data-driven clustering for blind feature mapping in speaker verification. In Proc. of interspeech (pp. 3109\u20133112)."},{"key":"9149_CR17","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/0167-6393(95)00009-D","volume":"17","author":"D. A. Reynolds","year":"1995","unstructured":"Reynolds, D. A. (1995). Speaker identification and verification using Gaussian mixture speaker models. Speech Communication, 17, 91\u2013108.","journal-title":"Speech Communication"},{"key":"9149_CR18","first-page":"6","volume-title":"Proc. of IEEE int. conf. acoust. speech signal processing (ICASSP)","author":"D. A. Reynolds","year":"2003","unstructured":"Reynolds, D. A. (2003). Channel robust speaker verification via feature mapping. In Proc. of IEEE int. conf. acoust. speech signal processing (ICASSP) (pp. 6\u201310)."},{"key":"9149_CR19","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1006\/dspr.1999.0361","volume":"10","author":"D. A. 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, 19\u201341.","journal-title":"Digital Signal Processing"},{"key":"9149_CR20","first-page":"81","volume-title":"Proc. of IEEE int. conf. acoust. speech signal processing (ICASSP)","author":"A. E. Rosenberg","year":"1996","unstructured":"Rosenberg, A. E., & Parthasarathy, S. (1996). Speaker background models for connected digit password speaker verification. In Proc. of IEEE int. conf. acoust. speech signal processing (ICASSP) (pp. 81\u201384)."},{"key":"9149_CR21","first-page":"599","volume-title":"Proc. of int. conf. spoken language processing (ICSLP)","author":"A. E. Rosenberg","year":"1992","unstructured":"Rosenberg, A. E., DeLong, J., Lee, C. -H., Jaung, B. -H., & Soong,\u00a0F.\u00a0K. (1992). The use of cohort normalized scores for speaker verification. In Proc. of int. conf. spoken language processing (ICSLP) (pp. 599\u2013602)."},{"key":"9149_CR22","doi-asserted-by":"crossref","first-page":"1233","DOI":"10.21437\/Interspeech.2008-374","volume-title":"Proc. of interspeech","author":"D. R. Sanand","year":"2008","unstructured":"Sanand, D. R., & Umesh, S. (2008). Study of Jacobian compensation using linear transformation of conventional MFCC for VTLN. In Proc. of interspeech (pp. 1233\u20131236)."},{"key":"9149_CR23","first-page":"286","volume-title":"Proc. of Odyssey speaker and language recognition workshop","author":"A. K. Sarkar","year":"2010","unstructured":"Sarkar, A. K., & Umesh, S. (2010). Investigation of speaker-clustered UBMs based on vocal tract lengths and MLLR matrices for speaker verification. In Proc. of Odyssey speaker and language recognition workshop (pp. 286\u2013293)."},{"key":"9149_CR24","doi-asserted-by":"crossref","first-page":"4552","DOI":"10.1109\/ICASSP.2011.5947367","volume-title":"Proc. of IEEE int. conf. acoust. speech signal processing (ICASSP)","author":"A. K. Sarkar","year":"2011","unstructured":"Sarkar, A. K., & Umesh, S. (2011). Use of VTL-wise models in feature-mapping framework to achieve performance of multiple-background models in speaker verification. In Proc. of IEEE int. conf. acoust. speech signal processing (ICASSP) (pp. 4552\u20134555)."},{"key":"9149_CR25","first-page":"2425","volume-title":"Proc. of Eur. conf. speech commun. and tech, Eurospeech","author":"A. Stolcke","year":"2005","unstructured":"Stolcke, A., Ferrer, L., Kajarekar, S., Shriberg, E., & Venkataraman, A. (2005). MLLR transforms as features in speaker recognition. In Proc. of Eur. conf. speech commun. and tech, Eurospeech (pp. 2425\u20132428)."},{"key":"9149_CR26","doi-asserted-by":"crossref","first-page":"741","DOI":"10.1109\/ICASSP.2005.1415220","volume-title":"Proc. of IEEE int. conf. acoust. speech signal processing (ICASSP)","author":"D. E. Sturim","year":"2005","unstructured":"Sturim, D. E., & Reynolds, D. (2005). Speaker adaptive cohort selection for t-norm in text-independent speaker verification. In Proc. of IEEE int. conf. acoust. speech signal processing (ICASSP) (pp. 741\u2013744)."},{"key":"9149_CR27","first-page":"495","volume-title":"Proc. of int. conf. spoken language processing (ICSLP)","author":"R. Teunen","year":"2000","unstructured":"Teunen, R., Shahshahani, B., & Heck, L. (2000). A model-based transformational approach to robust speaker recognition. In Proc. of int. conf. spoken language processing (ICSLP) (pp. 495\u2013498)."},{"key":"9149_CR28","unstructured":"The Evaluation Plan of NIST 2004 Speaker Recognition Campaign (2004). http:\/\/www.itl.nist.gov\/iad\/mig\/\/tests\/sre\/2004\/SRE04_evalplan-v1a.pdf ."},{"key":"9149_CR29","first-page":"1069","volume-title":"Proc. of IEEE int. conf. acoust. speech signal processing (ICASSP)","author":"D. Tran","year":"2000","unstructured":"Tran, D., & Wagner, M. (2000). A proposed likelihood transformation for speaker verification. In Proc. of IEEE int. conf. acoust. speech signal processing (ICASSP) (pp. 1069\u20131072)."},{"key":"9149_CR30","first-page":"3205","volume-title":"Proc. of int. conf. spoken language processing (ICSLP)","author":"S. V. Vuuren","year":"1998","unstructured":"Vuuren, S. V., & Hermansky, H. (1998). On the importance of components of the modulation spectrum for speaker verification. In Proc. of int. conf. spoken language processing (ICSLP) (pp. 3205\u20133208)."},{"key":"9149_CR31","first-page":"47","volume-title":"Proc. of Odyssey speaker and language recognition workshop","author":"W. Q. Zhang","year":"2010","unstructured":"Zhang, W. Q., Shan, Y., & Liu, J. (2010). Multiple background models for speaker verification. In Proc. of Odyssey speaker and language recognition workshop (pp. 47\u201351)."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-012-9149-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-012-9149-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-012-9149-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,25]],"date-time":"2024-04-25T18:07:47Z","timestamp":1714068467000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-012-9149-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,6,15]]},"references-count":31,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2012,9]]}},"alternative-id":["9149"],"URL":"https:\/\/doi.org\/10.1007\/s10772-012-9149-1","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,6,15]]}}}