{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:27:07Z","timestamp":1740122827681,"version":"3.37.3"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,2,5]],"date-time":"2019-02-05T00:00:00Z","timestamp":1549324800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2019,3]]},"DOI":"10.1007\/s10772-018-09587-1","type":"journal-article","created":{"date-parts":[[2019,2,5]],"date-time":"2019-02-05T07:45:54Z","timestamp":1549352754000},"page":"231-249","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Segment-level probabilistic sequence kernel and segment-level pyramid match kernel based extreme learning machine for classification of varying length patterns of speech"],"prefix":"10.1007","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0574-2543","authenticated-orcid":false,"given":"Shikha","family":"Gupta","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmed","family":"Karanath","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kansul","family":"Mahrifa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A. D.","family":"Dileep","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Veena","family":"Thenkanidiyoor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,2,5]]},"reference":[{"key":"9587_CR3","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.patrec.2014.12.003","volume":"54","author":"I Alexandos","year":"2015","unstructured":"Alexandos, I., Tefas, A., & Pitas, ioannis. (2015). On the kernel extreme learning machine classifiers. Pattern Recognition Letters, 54, 11\u201317.","journal-title":"Pattern Recognition Letters"},{"issue":"Dec","key":"9587_CR4","first-page":"113","volume":"1","author":"EL Allwein","year":"2000","unstructured":"Allwein, E. L., Schapire, R. E., & Singer, Y. (2000). Reducing multiclass to binary: A unifying approach for margin classifiers. Journal of Machine Learning Research, 1(Dec), 113\u2013141.","journal-title":"Journal of Machine Learning Research"},{"key":"9587_CR5","doi-asserted-by":"crossref","unstructured":"Boughorbel, S., Tarel, J. P., & Boujemaa, N. (2005). The intermediate matching kernel for image local features. In Proceedings of the International Joint Conference on Neural Networks (IJCNN 2005) (pp. 889\u2013894), Montreal","DOI":"10.1109\/IJCNN.2005.1555970"},{"key":"9587_CR6","doi-asserted-by":"crossref","unstructured":"Burkhardt, F., Paeschke, A., Rolfes, M., & Weiss, W. S. B. (2005). A database of German emotional speech. In Proceedings of INTERSPEECH (pp. 1517\u20131520), Lisbon.","DOI":"10.21437\/Interspeech.2005-446"},{"issue":"5","key":"9587_CR34","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. D. E. (2006). Support vector machines using GMM supervectors for speaker verification. IEEE Signal Processing Letters, 13(5), 308\u2013311.","journal-title":"IEEE Signal Processing Letters"},{"issue":"3","key":"9587_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1961189.1961199","volume":"2","author":"CC Chang","year":"2011","unstructured":"Chang, C. C., & Linm, C. J. (2011). LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2(3), 1\u201327. http:\/\/www.csie.ntu.edu.tw\/cjlin\/libsvm .","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"key":"9587_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Yh., Lopez-Moreno, I., Sainath, T., Visontai, M., Alvarez, R., & Parada, C. (2015). Locally connected and convolutional neural networks for small footprint speaker recognition. In Proceedings of INTERSPEECH (pp. 1136\u20131140), Dresden.","DOI":"10.21437\/Interspeech.2015-297"},{"key":"9587_CR9","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1016\/j.neucom.2013.08.009","volume":"128","author":"J Chorowski","year":"2014","unstructured":"Chorowski, J., Wang, J., & Zurada, J. M. (2014). Review and performance comparison of svm-and elm-based classifiers. Neurocomputing, 128, 507\u2013516.","journal-title":"Neurocomputing"},{"issue":"3","key":"9587_CR10","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1007\/s10772-012-9154-4","volume":"15","author":"AD Dileep","year":"2012","unstructured":"Dileep, A. D., & Chandra Sekhar, C. (2012). Speaker recognition using pyramid match kernel based support vector machines. Internatiional Journal for Speech Technology, 15(3), 365\u2013379.","journal-title":"Internatiional Journal for Speech Technology"},{"issue":"8","key":"9587_CR11","doi-asserted-by":"publisher","first-page":"1421","DOI":"10.1109\/TNNLS.2013.2293512","volume":"25","author":"AD Dileep","year":"2014","unstructured":"Dileep, A. D., & Chandra Sekhar, C. (2014). GMM-based intermediate matching kernel for classification of varying length patterns of long duration speech using support vector machines. IEEE Transactions on Neural Networks and Learning Systems, 25(8), 1421\u20131432.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"17","key":"9587_CR12","doi-asserted-by":"publisher","first-page":"1271","DOI":"10.1109\/TPAMI.2009.132","volume":"32","author":"Veenman CJ Gemert","year":"2010","unstructured":"Gemert, Veenman C. J., Smeulders, A. W. M., & Geusebroek, J. M. (2010). Visual word ambiguity. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(17), 1271\u20131283.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"725\/36","key":"9587_CR13","first-page":"725","volume":"10","author":"G Gordon","year":"2012","unstructured":"Gordon, G., & Tibshirani, R. (2012). Karush-kuhn-tucker conditions. Optimization, 10(725\/36), 725.","journal-title":"Optimization"},{"key":"9587_CR14","first-page":"725","volume":"8","author":"K Grauman","year":"2007","unstructured":"Grauman, K., & Darrell, T. (2007). The pyramid match kernel: Efficient learning with sets of features. The Journal of Machine Learning Research, 8, 725\u2013760.","journal-title":"The Journal of Machine Learning Research"},{"key":"9587_CR15","doi-asserted-by":"crossref","unstructured":"Gupta, S., Dileep, A. D., & Thenkanidiyoor, V. (2016a). Segment-level pyramid match kernels for the classification of varying length patterns of speech using svms. In Signal Processing Conference (EUSIPCO), 2016 24th European, IEEE (pp. 2030\u20132034).","DOI":"10.1109\/EUSIPCO.2016.7760605"},{"key":"9587_CR16","doi-asserted-by":"crossref","unstructured":"Gupta, S., Thenkanidiyoor, V., & Dileep, A. D. (2016b). Segment-level probabilistic sequence kernel based support vector machines for classification of varying length patterns of speech. In International Conference on Neural Information Processing (pp. 321\u2013328). New York: Springer.","DOI":"10.1007\/978-3-319-46681-1_39"},{"issue":"3","key":"9587_CR17","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1007\/s12559-014-9255-2","volume":"6","author":"G Huang","year":"2014","unstructured":"Huang, G. (2014). An insight into extreme learning machines: Random neurons, random features and kernels. Cognitive Computation, 6(3), 376\u2013390. https:\/\/doi.org\/10.1007\/s12559-014-9255-2 .","journal-title":"Cognitive Computation"},{"issue":"4","key":"9587_CR18","doi-asserted-by":"publisher","first-page":"879","DOI":"10.1109\/TNN.2006.875977","volume":"17","author":"GB Huang","year":"2006","unstructured":"Huang, G. B., Chen, L., & Siew, C. K. (2006). Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Transactions on Neural Networks, 17(4), 879\u2013892.","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"2","key":"9587_CR19","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1109\/TSMCB.2011.2168604","volume":"42","author":"GB Huang","year":"2012","unstructured":"Huang, G. B., Zhou, H., Ding, X., et al. (2012). Extreme learning machine for regression and multiclass classification. IEEE Transactions on Systems, Man, and Cybernetics, B (Cybernetics), 42(2), 513\u2013529.","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics, B (Cybernetics)"},{"key":"9587_CR21","doi-asserted-by":"crossref","unstructured":"Lee, K. A., HTK You, C. H. (2007). A GMM-based probabilistic sequence kernel for speaker verification. In Proceedings of INTERSPEECH, (pp. 294\u2013297), Antwerp.","DOI":"10.21437\/Interspeech.2007-131"},{"key":"9587_CR22","doi-asserted-by":"crossref","unstructured":"Lazebnik, S., Schmid, C., & Ponce, J. (2006). Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), (vol.\u00a02, pp. 2169\u20132178), New York.","DOI":"10.1109\/CVPR.2006.68"},{"issue":"8","key":"9587_CR23","doi-asserted-by":"publisher","first-page":"2203","DOI":"10.1109\/TMM.2014.2360798","volume":"16","author":"Q Mao","year":"2014","unstructured":"Mao, Q., Dong, M., Huang, Z., & Zhan, Y. (2014). Learning salient features for speech emotion recognition using convolutional neural networks. IEEE Transactions on Multimedia, 16(8), 2203\u20132213.","journal-title":"IEEE Transactions on Multimedia"},{"issue":"8","key":"9587_CR24","doi-asserted-by":"publisher","first-page":"857","DOI":"10.1002\/(SICI)1097-0258(19980430)17:8<857::AID-SIM777>3.0.CO;2-E","volume":"17","author":"RG Newcombe","year":"1998","unstructured":"Newcombe, R. G. (1998). Two-sided confidence intervals for the single proportion: Comparison of seven methods. Statistics in Medicine, 17(8), 857\u2013872.","journal-title":"Statistics in Medicine"},{"key":"9587_CR25","unstructured":"Rabiner, L., & Juang, B. H. (2003). Fundamentals of Speech Recognition. Pearson Education."},{"key":"9587_CR26","volume-title":"Generalized inverse of matrices and its applications","author":"CR Rao","year":"1971","unstructured":"Rao, C. R., & Mitra, S. K. (1971). Generalized inverse of matrices and its applications (Vol. 7). New York: Wiley."},{"key":"9587_CR27","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/0167-6393(95)00009-D","volume":"17","author":"DA 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"},{"issue":"1\u20133","key":"9587_CR28","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(1\u20133), 19\u201341.","journal-title":"Digital Signal Processing"},{"key":"9587_CR30","doi-asserted-by":"crossref","unstructured":"Sachdev, A., Dileep, A. D., & Thenkanidiyoor, V. (2015). Example-specific density based matching kernel for classification of varying length patterns of speech using support vector machines. In Proceedings of ICONIP, (pp. 177\u2013184). Istanbul.","DOI":"10.1109\/ISCMI.2015.22"},{"key":"9587_CR31","unstructured":"Smith, N., Gales, M., & Niranjan, M. (2001). Data-dependent kernels in SVM classification of speech patterns. Tech. Rep. CUED\/F-INFENG\/TR.387, Cambridge University Engineering Department, Cambridge."},{"key":"9587_CR29","unstructured":"Steidl, S. (2009). Automatic classification of emotion-related user states in spontaneous childern\u2019s speech. PhD thesis, Der Technischen Fakult\u00e4t der Universit\u00e4t Erlangen-N\u00fcrnberg, Germany."},{"issue":"1","key":"9587_CR32","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/BF00130487","volume":"7","author":"MJ Swain","year":"1991","unstructured":"Swain, M. J., & Ballard, D. H. (1991). Color indexing. International Journal of Computer Vision, 7(1), 11\u201332.","journal-title":"International Journal of Computer Vision"},{"key":"9587_CR1","unstructured":"The NIST Year 2002 Speaker Recognition Evaluation Plan. (2002). http:\/\/www.itlnistgov\/iad\/mig\/tests\/spk\/2002\/"},{"key":"9587_CR2","unstructured":"The NIST Year 2003 Speaker Recognition Evaluation Plan. (2003). http:\/\/www.itlnistgov\/iad\/mig\/tests\/sre\/2003\/"},{"key":"9587_CR33","doi-asserted-by":"crossref","unstructured":"Vedaldi, A., & Zisserman, A. (2010). Efficient additive kernels via explicit feature maps. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (pp. 3539\u20133546).","DOI":"10.1109\/CVPR.2010.5539949"},{"key":"9587_CR20","unstructured":"Wang J., KYFLTH Yang, J., & Gong, Y. (2010). Locality-constrained linear coding for image classification. In Proceedings of CVPR\u201910, IEEE (pp. 3360\u20133367). State College: The Pennsylvania State University."},{"key":"9587_CR35","unstructured":"Yang, J., Yu, K., Gong, Y., & Huang, T. (2009). Linear spatial pyramid matching using sparse coding for image classification. In Proceedings of CVPR\u201909, IEEE, (pp. 1794\u20131801)."},{"issue":"1","key":"9587_CR36","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1109\/LSP.2008.2006711","volume":"16","author":"CH You","year":"2009","unstructured":"You, C. H., Lee, K. A., & Li, H. (2009). An SVM kernel with GMM-supervector based on the Bhattacharyya distance for speaker recognition. IEEE Signal Processing Letters, 16(1), 49\u201352.","journal-title":"IEEE Signal Processing Letters"},{"key":"9587_CR37","unstructured":"Zhang, L., Zhang, D., & Tian, F. (2016). Svm and elm: Who wins? object recognition with deep convolutional features from imagenet. In Proceedings of ELM-2015 (Vol. 1, pp. 249\u2013263). Springer: New York."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-018-09587-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-018-09587-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-018-09587-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,11]],"date-time":"2022-09-11T11:38:43Z","timestamp":1662896323000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-018-09587-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,5]]},"references-count":37,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,3]]}},"alternative-id":["9587"],"URL":"https:\/\/doi.org\/10.1007\/s10772-018-09587-1","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2019,2,5]]},"assertion":[{"value":"10 August 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 December 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 February 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}