{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T00:15:59Z","timestamp":1725495359988},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,7,13]],"date-time":"2021-07-13T00:00:00Z","timestamp":1626134400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,7,13]],"date-time":"2021-07-13T00:00:00Z","timestamp":1626134400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2021,12]]},"DOI":"10.1007\/s10772-021-09862-8","type":"journal-article","created":{"date-parts":[[2021,7,13]],"date-time":"2021-07-13T15:03:24Z","timestamp":1626188604000},"page":"1067-1088","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Utterance partitioning for speaker recognition: an experimental review and analysis with new findings under GMM-SVM framework"],"prefix":"10.1007","volume":"24","author":[{"given":"Nirmalya","family":"Sen","sequence":"first","affiliation":[]},{"given":"Md","family":"Sahidullah","sequence":"additional","affiliation":[]},{"given":"Hemant A.","family":"Patil","sequence":"additional","affiliation":[]},{"given":"Shyamal Kumar","family":"Das Mandal","sequence":"additional","affiliation":[]},{"given":"Krothapalli Sreenivasa","family":"Rao","sequence":"additional","affiliation":[]},{"given":"Tapan Kumar","family":"Basu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,7,13]]},"reference":[{"key":"9862_CR1","volume-title":"Introduction to machine learning","author":"E Alpaydin","year":"2004","unstructured":"Alpaydin, E. (2004). Introduction to machine learning (2nd ed.). Cambridge: MIT Press.","edition":"2"},{"key":"9862_CR2","unstructured":"Bilmes, J. A. (1998). A gentle tutorial of the EM algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models. Tech. Rep. ICSI-TR-97\u2013021, Department of Electrical Engineering and Computer Science,U.C. Berkeley. pp. 1\u201315."},{"issue":"2","key":"9862_CR3","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1023\/A:1009715923555","volume":"2","author":"CJC Burges","year":"1998","unstructured":"Burges, C. J. C. (1998). A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery, 2(2), 121\u2013167.","journal-title":"Data Mining and Knowledge Discovery"},{"issue":"5","key":"9862_CR4","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1109\/LSP.2006.870086","volume":"13","author":"WM Campbell","year":"2006","unstructured":"Campbell, W. M., Sturim, D. E., & Reynolds, D. A. (2006a). Support vector machines using GMM supervectors for speaker verification. IEEE Signal Processing Letters, 13(5), 308\u2013311.","journal-title":"IEEE Signal Processing Letters"},{"key":"9862_CR5","doi-asserted-by":"crossref","unstructured":"Campbell,W.M., Sturim, D.E., Reynolds, D.A. & Solomonoff, A. (2006b). SVM based speaker verification using a GMM supervector kernel and NAP variability compensation. In: ICASSP06, vol. 1, pp 97\u2013100.","DOI":"10.1109\/ICASSP.2006.1659966"},{"key":"9862_CR6","unstructured":"Chakroborty, S. (2008). Some studies on acoustic feature extraction, feature selection and multi-level fusion strategies for robust text-independent speaker identification. Ph.D. Thesis, department of electronics and electrical communication engineering, IIT Kharagpur, India."},{"key":"9862_CR7","unstructured":"Chang, C.-C. & Lin, C.-J. (2001). LIBSVM: A Library for Support Vector Machines. [Online]. http:\/\/www.csie.ntu.edu.tw\/~cjlin\/libsvm"},{"issue":"4","key":"9862_CR8","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"SB Davis","year":"1980","unstructured":"Davis, S. B., & Mermelsteine, P. (1980). Comparison of parametric representation for monosyllabic word recognition in continuously spoken sentences. IEEE Transactions Acousting, Speech, Signal Processing ASSP, 28(4), 357\u2013365.","journal-title":"IEEE Transactions Acousting, Speech, Signal Processing ASSP"},{"key":"9862_CR9","doi-asserted-by":"crossref","unstructured":"Dehak, N., Chollet, G. (2006). Support vector GMMs for speaker verification. In: Proc. IEEE Odyssey: the Speaker and Language Recognition Workshop (Odyssey 2006), San Juan, Puerto Rico, June 2006.","DOI":"10.1109\/ODYSSEY.2006.248131"},{"issue":"4","key":"9862_CR10","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2010","unstructured":"Dehak, N., Kenny, P. J., Dehak, R., Dumouchel, P., & Ouellet, P. (2010). 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":"9862_CR11","doi-asserted-by":"crossref","unstructured":"Fauve, B., Evans, N., Pearson, N., Bonastre, J.-F., Mason, J. (2007). Influence of task duration in text-independent speaker verification. In: Proc. Interspeech2007, Antwerp, Belgium, pp. 794\u2013797.","DOI":"10.21437\/Interspeech.2007-151"},{"issue":"6","key":"9862_CR12","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1109\/MSP.2015.2462851","volume":"32","author":"JH Hansen","year":"2015","unstructured":"Hansen, J. H., & Hasan, T. (2015). Speaker recognition by machines and humans: A tutorial review. IEEE Signal Processing Magazine, 32(6), 74\u201399.","journal-title":"IEEE Signal Processing Magazine"},{"key":"9862_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.specom.2017.10.002","volume":"95","author":"RG Hautam\u00e4ki","year":"2017","unstructured":"Hautam\u00e4ki, R. G., Sahidullah, M., Hautam\u00e4ki, V., & Kinnunen, T. (2017). Acoustical and perceptual study of voice disguise by age modification in speaker verification. Speech Communication, 95, 1\u201315.","journal-title":"Speech Communication"},{"issue":"2","key":"9862_CR14","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/s10772-017-9402-8","volume":"20","author":"A Kanagasundaram","year":"2017","unstructured":"Kanagasundaram, A., Dean, D., Sridharan, S., Ghaemmaghami, H., & Fookes, C. (2017). A study on the effects of using short utterance length development data in the design of GPLDA speaker verification systems. International Journal of Speech Technology, 20(2), 247\u2013259.","journal-title":"International Journal of Speech Technology"},{"key":"9862_CR15","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.specom.2014.01.004","volume":"59","author":"A Kanagasundaram","year":"2014","unstructured":"Kanagasundaram, A., Dean, D., Sridharan, S., Gonzalez-Dominguez, J., Gonzalez-Rodriguez, J., & Ramos, D. (2014). Improving short utterance i-vector speaker verification using utterance variance modelling and compensation techniques. Speech Communication, 59, 69\u201382.","journal-title":"Speech Communication"},{"key":"9862_CR16","unstructured":"Kandali, A. B. (2012). Classification of discrete emotions in speech using prosodic and spectral features: Intra and cross-lingual studies in five native languages of Assam. Ph.D. Thesis, department of electrical engineering, IIT Kharagpur, India."},{"issue":"1","key":"9862_CR17","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.specom.2009.08.009","volume":"52","author":"T Kinnunen","year":"2010","unstructured":"Kinnunen, T., & Li, H. (2010). An overview of text-independent speaker recognition: From features to supervectors. Speech Communication, 52(1), 12\u201340.","journal-title":"Speech Communication"},{"key":"9862_CR18","unstructured":"Kinnunen, T. (2004). Spectral features for automatic text-independent speaker recognition. Ph.D. Thesis, University of Joensuu."},{"issue":"4","key":"9862_CR19","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1016\/j.patrec.2008.11.007","volume":"30","author":"T Kinnunen","year":"2009","unstructured":"Kinnunen, T., Saastamoinen, J., Hautam\u00e4ki, V., Vinni, M., & Franti, P. (2009). Comparative evaluation of maximum a posteriori vector quantization and Gaussian mixture models in speaker verification. Pattern Recognition Letters., 30(4), 341\u2013347.","journal-title":"Pattern Recognition Letters."},{"issue":"1","key":"9862_CR20","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.specom.2010.06.011","volume":"53","author":"MW Mak","year":"2011","unstructured":"Mak, M. W., & Rao, W. (2011). Utterance partitioning with acoustic vector resampling for GMM\u2013SVM speaker verification. Speech Communication, 53(1), 119\u2013130.","journal-title":"Speech Communication"},{"key":"9862_CR21","doi-asserted-by":"crossref","unstructured":"Mat\u011bjka, P., Glembek, O., Castaldo, F., Alam, M.J., Plchot, O., Kenny, P., Burget, L. and \u010cernocky, J. (May 2011). Full-covariance UBM and heavy-tailed PLDA in i-vector speaker verification. In 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 4828\u20134831).","DOI":"10.1109\/ICASSP.2011.5947436"},{"key":"9862_CR22","unstructured":"Patil, H. A. (2005). Speaker Recognition in Indian Languages: A Feature Based Approach. Ph.D. Thesis, department of electrical engineering, IIT Kharagpur, India."},{"key":"9862_CR23","unstructured":"Petrovska, D., et al. (1998). POLYCOST: A Telephonic speech database for speaker recognition. RLA2C, Avignon, France, April 20\u201323, pp. 211\u2013214."},{"issue":"2","key":"9862_CR24","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1049\/iet-bmt.2017.0065","volume":"7","author":"A Poddar","year":"2017","unstructured":"Poddar, A., Sahidullah, M., & Saha, G. (2017). Speaker verification with short utterances: A review of challenges, trends and opportunities. IET Biometrics, 7(2), 91\u2013101.","journal-title":"IET Biometrics"},{"issue":"5","key":"9862_CR25","doi-asserted-by":"publisher","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"},{"key":"9862_CR26","doi-asserted-by":"publisher","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, 19\u201341.","journal-title":"Digital Signal Processing"},{"key":"9862_CR27","unstructured":"Sahidullah, Md. (2015). Enhancement of speaker recognition performance using block level, relative, and temporal information of subband energies. Ph.D. Thesis, Department of Electronics and Electrical Communication Engineering, IIT Kharagpur, India."},{"issue":"4","key":"9862_CR28","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1016\/j.specom.2011.11.004","volume":"54","author":"Md Sahidullah","year":"2012","unstructured":"Sahidullah, Md., & Saha, G. (2012). Design, analysis and experimental evaluation of block based transformation in MFCC computation for speaker recognition. Speech Communication., 54(4), 543\u2013565.","journal-title":"Speech Communication."},{"key":"9862_CR29","unstructured":"Sen, N. (2014). Enhancement of speaker recognition performance for short test segments using GMM-SVM and polynomial classifiers. Ph.D. Thesis, Centre for Educational Technology, IIT Kharagpur, India."},{"key":"9862_CR30","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Sell, G., Povey, D. & Khudanpur, S., 2018, April. X-vectors: Robust dnn embeddings for speaker recognition. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 5329\u20135333).","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"9862_CR31","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2440-0","volume-title":"The nature of statistical learning theory","author":"V Vapnik","year":"1995","unstructured":"Vapnik, V. (1995). The nature of statistical learning theory. Springer-Verlag."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09862-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-021-09862-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09862-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T01:40:11Z","timestamp":1725414011000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-021-09862-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,13]]},"references-count":31,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["9862"],"URL":"https:\/\/doi.org\/10.1007\/s10772-021-09862-8","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2021,7,13]]},"assertion":[{"value":"6 November 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 May 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 July 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}