{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T04:27:55Z","timestamp":1688185675318},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2013,4,18]],"date-time":"2013-04-18T00:00:00Z","timestamp":1366243200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2014,4]]},"DOI":"10.1007\/s11063-013-9299-4","type":"journal-article","created":{"date-parts":[[2013,4,17]],"date-time":"2013-04-17T11:13:53Z","timestamp":1366197233000},"page":"195-218","source":"Crossref","is-referenced-by-count":7,"title":["Extension of a Kernel-Based Classifier for Discriminative Spoken Keyword Spotting"],"prefix":"10.1007","volume":"39","author":[{"given":"Shima","family":"Tabibian","sequence":"first","affiliation":[]},{"given":"Ahmad","family":"Akbari","sequence":"additional","affiliation":[]},{"given":"Babak","family":"Nasersharif","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2013,4,18]]},"reference":[{"key":"9299_CR1","volume-title":"Fundamentals of speech recognition","author":"LR Rabiner","year":"2010","unstructured":"Rabiner LR, Juang B, Yegnanarayana B (2010) Fundamentals of speech recognition. Pearson, New Delhi"},{"key":"9299_CR2","volume-title":"Theory and application of digital speech processing","author":"LR Rabiner","year":"2011","unstructured":"Rabiner LR, Schafer RW (2011) Theory and application of digital speech processing, 1st edn. Prentice Hall, New York","edition":"1"},{"key":"9299_CR3","volume-title":"Discrete-time processing of speech signals","author":"JR Deller","year":"2000","unstructured":"Deller JR, Hansen JHL, Proakis JG (2000) Discrete-time processing of speech signals. IEEE Press, New York"},{"key":"9299_CR4","doi-asserted-by":"crossref","unstructured":"Ghaffari A, Homaeinezhad MR, Daevaeiha MM (2011) High resolution ambulatory holter ECG events detection-delineation via modified multi-lead wavelet-based features analysis: detection and quantification of heart rate turbulence. Expert Syst Appl 38:5299\u20135310","DOI":"10.1016\/j.eswa.2010.10.028"},{"key":"9299_CR5","doi-asserted-by":"crossref","unstructured":"Wang D, Tejedor J, Frankel J, King S, Colas J (2009) Posterior-based confidence measures for spoken term detection. In: Proceedings of ICASSP, pp 4889\u20134892","DOI":"10.1109\/ICASSP.2009.4960727"},{"key":"9299_CR6","unstructured":"Rose RC, Paul DB (1990) A hidden Markov model based keyword recognition system. In: Proceedings of ICASSP, pp 129\u2013132"},{"key":"9299_CR7","doi-asserted-by":"crossref","first-page":"980","DOI":"10.1016\/j.specom.2008.03.005","volume":"50","author":"J Tejedor","year":"2008","unstructured":"Tejedor J, Wang D, Frankel J, King S, Col\u00e1s J (2008) A comparison of grapheme and phone-based units for Spanish spoken term detection. Speech Commun 50:980\u2013991","journal-title":"Speech Commun"},{"key":"9299_CR8","doi-asserted-by":"crossref","unstructured":"Fernandez S, Graves A, Schmidhuber J (2007) An application of recurrent neural networks to discriminative keyword spotting. In: International conference on artificial, neural networks (ICANN), pp 220\u2013229","DOI":"10.1007\/978-3-540-74695-9_23"},{"key":"9299_CR9","unstructured":"Li KP, Naylor JA, Rossen ML (1992) A whole word recurrent neural network for keyword spotting. In IEEE international conference on acoustics, speech, and signal processing (ICASSP), pp 81\u201384"},{"key":"9299_CR10","volume-title":"An introduction to support vector machines","author":"N Cristianini","year":"2000","unstructured":"Cristianini N, Shawe-Taylor J (2000) An introduction to support vector machines. Cambridge University Press, Cambridge"},{"key":"9299_CR11","volume-title":"Statistical learning theory","author":"VN Vapnik","year":"1998","unstructured":"Vapnik VN (1998) Statistical learning theory. Wiley, New York"},{"key":"9299_CR12","unstructured":"Altun Y, Tsochantaridis I, Hofmann Th (2003) Hidden Markov support vector machines. In: Proceedings of the twentieth international conference on machine learning"},{"key":"9299_CR13","unstructured":"Bahl LR, Brown PF, de Souza P, Mercer RL (1989) Maximum mutual information estimation of hidden Markov model parameters for speech recognition. In: IEEE international conference on acoustics, speech, and signal processing (ICASSP), pp 49\u201352"},{"key":"9299_CR14","doi-asserted-by":"crossref","first-page":"3043","DOI":"10.1109\/78.175747","volume":"40","author":"B Juang","year":"1992","unstructured":"Juang B, Katagiri S (1992) Discriminative learning for minimum error classification. IEEE Trans Signal Process 40:3043\u20133054","journal-title":"IEEE Trans Signal Process"},{"key":"9299_CR15","unstructured":"Povey D, Woodland P (2002) Minimum phone error and I-smoothing for improved discriminative training. In: International conference on acoustics, speech, and signal processing (ICASSP), pp 105\u2013108"},{"key":"9299_CR16","unstructured":"Tabibian Sh, Akbari A, Nasersharif B (2011) An evolutionary based discriminative system for keyword spotting. In: Symposium on artificial intelligence and signal processing (AISP2011), indexed by IEEE, pp 83\u201388"},{"key":"9299_CR17","doi-asserted-by":"crossref","DOI":"10.1002\/9780470742044","volume-title":"Automatic speech and speaker recognition. Large margin and kernel methods","author":"J Keshet","year":"2009","unstructured":"Keshet J, Bengio S (2009) Automatic speech and speaker recognition. Large margin and kernel methods. Wiley, New York"},{"key":"9299_CR18","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1016\/j.specom.2008.10.002","volume":"51","author":"J Keshet","year":"2009","unstructured":"Keshet J, Grangier D, Bengio S (2009) Discriminative keyword spotting. Speech Commun 51:317\u2013329","journal-title":"Speech Commun"},{"key":"9299_CR19","unstructured":"Tabibian Sh, Shokri A, Akbari A, Nasersharif B (2010) Performance evaluation for an HMM-based keyword spotter and a Large-margin based one in noisy environments. In: World conference on information technology, procedia computer science, vol 3, pp 1018\u20131022"},{"key":"9299_CR20","unstructured":"Salomon J, King S, Osborne M (2002) Frame wise phone classification using support vector machines. In: Proceedings of the seventh international conference on spoken language processing, pp 2645\u20132648"},{"key":"9299_CR21","unstructured":"Ganapathiraju A, Hamaker J, Picone J (2002) Support vector machines for speech recognition. In: Proceedings of the international conference on spoken language processing"},{"key":"9299_CR22","unstructured":"Padrell-Sendra1 J, Martin-Iglesias D, Diaz-de-Maria F (2006) Support vector machines for continuous speech recognition. In: European signal processing conference (EUSIPCO), pp 2\u20135"},{"key":"9299_CR23","doi-asserted-by":"crossref","unstructured":"Bardideh M, Razzazi F, Ghassemian H (2007) An SVM-based confidence measure for continuous speech recognition. In: IEEE international conference on signal processing and communications (ICSPC), pp 24\u201327","DOI":"10.1109\/ICSPC.2007.4728494"},{"key":"9299_CR24","doi-asserted-by":"crossref","unstructured":"Benayed Y, Fohr D, Haton JP, Chollet G (2003) Improving the performance of a keyword spotting system by using support vector machines. In: IEEE workshop on automatic speech recognition and understanding (ASRU), pp 145\u2013149","DOI":"10.1109\/ASRU.2003.1318419"},{"key":"9299_CR25","doi-asserted-by":"crossref","unstructured":"Ben Ayed Y, Fohr D, Haton JP, Chollet G (2002) Keyword spotting using support vector machines. In: Proceedings of the international conference on text, speech and dialogue, pp 285\u2013292","DOI":"10.1007\/3-540-46154-X_39"},{"key":"9299_CR26","doi-asserted-by":"crossref","unstructured":"Zhi-yi Q, Yu L, Li-hong Zh, Ming-xin Sh (2006) A speech recognition system based on a hybrid HMM\/SVM architecture. In: Proceedings of the first international conference on innovative computing, information and control (ICICIC), pp 100\u2013104","DOI":"10.1109\/ICICIC.2006.221"},{"key":"9299_CR27","doi-asserted-by":"crossref","unstructured":"Solera-Urena R, Padrell-Sendra J, Mart\u00edn-Iglesias D, Gallardo-Antol\u00edn A, Pel\u00e1aez-Moreno C, D\u00edaz-de-Mar\u00eda F (2007) SVMs for automatic speech recognition: a survey. Progress in nonlinear speech processing. Springer, New York, pp 190\u2013216","DOI":"10.1007\/978-3-540-71505-4_11"},{"key":"9299_CR28","unstructured":"Hejazi SA, Kazemi R, Ghaemmaghami S (2008) Isolated Persian digit recognition using a hybrid HMM-SVM. In: International symposium on intelligent signal processing and communication systems (ISPACS), pp 1\u20134"},{"key":"9299_CR29","doi-asserted-by":"crossref","unstructured":"Huang H, Zhu J (2006) Kernel-based non-linear feature extraction methods for speech recognition. In: Proceedings of the sixth international conference on intelligent systems design and applications (ISDA), pp 749\u2013754","DOI":"10.1109\/ISDA.2006.253706"},{"key":"9299_CR30","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1007\/s11063-004-0036-x","volume":"22","author":"WM Zheng","year":"2005","unstructured":"Zheng WM, Zou CR, Zhao L (2005) An improved algorithm for kernel principle components analysis. Neural Process Lett 22:49\u201356","journal-title":"Neural Process Lett"},{"issue":"2","key":"9299_CR31","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1007\/s11063-011-9170-4","volume":"33","author":"R Zhang","year":"2011","unstructured":"Zhang R, Wang W (2011) Learning linear and nonlinear PCA with linear programming. Neural Process Lett 33(2):151\u2013170","journal-title":"Neural Process Lett"},{"key":"9299_CR32","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1016\/S0925-2312(03)00444-2","volume":"56","author":"J Yang","year":"2004","unstructured":"Yang J, Frangi AF, Yang JY (2004) A new kernel Fisher discriminant algorithm with application to face recognition. Neurocomputing 56:415\u2013421","journal-title":"Neurocomputing"},{"key":"9299_CR33","doi-asserted-by":"crossref","first-page":"1026","DOI":"10.1016\/j.patcog.2005.10.029","volume":"39","author":"Y Xu","year":"2006","unstructured":"Xu Y, Zhang D, Jin Zh, Li M, Yang JY (2006) A fast kernel-based nonlinear discriminant analysis for multi-class problems. Pattern Recognit 39:1026\u20131033","journal-title":"Pattern Recognit"},{"key":"9299_CR34","volume-title":"Pattern recognition","author":"S Theodoridis","year":"2009","unstructured":"Theodoridis S, Koutroumbas K (2009) Pattern recognition, 2nd edn. Elsevier, Amsterdam","edition":"2"},{"key":"9299_CR35","volume-title":"Algorithms and architectures for machine learning based on regularized neural networks and support vector approaches","author":"M Rychetsky","year":"2001","unstructured":"Rychetsky M (2001) Algorithms and architectures for machine learning based on regularized neural networks and support vector approaches. Shaker Verlag, Berlin"},{"key":"9299_CR36","doi-asserted-by":"crossref","DOI":"10.1142\/5089","volume-title":"Least squares support vector machines","author":"JAK Suykens","year":"2002","unstructured":"Suykens JAK, Van Gestel T, De Brabanter J, De Moor B, Vanthienen J (2002) Least squares support vector machines. World Scientific, Singapore"},{"key":"9299_CR37","doi-asserted-by":"crossref","unstructured":"Salomon J, King S, Osborne M (2002) Frame wise phone classification using support vector machines. In: Proceedings of the seventh international conference on spoken language processing (ICSLP2002-INTERSPEECH)","DOI":"10.21437\/ICSLP.2002-352"},{"key":"9299_CR38","doi-asserted-by":"crossref","unstructured":"Keshet J, Shalev-Shwartz S, Bengio S, Singer Y, Chazan D (2006) Discriminative kernel-based phoneme sequence recognition. In: Proceedings of international conference on spoken, language processing (INTERSPEECH)","DOI":"10.21437\/Interspeech.2006-217"},{"key":"9299_CR39","unstructured":"Dekel O, Keshet J, Singer Y (2004) Online algorithm for hierarchical phoneme classification. In Workshop on machine learning for multimodal interaction, pp 146\u2013158"},{"key":"9299_CR40","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1109\/MSP.2004.1296543","volume":"21","author":"F Perez-Cruz","year":"2004","unstructured":"Perez-Cruz F, Bousquet O (2004) Kernel methods and their potential use in signal processing. IEEE Signal Process Mag 21:57\u201365","journal-title":"IEEE Signal Process Mag"},{"key":"9299_CR41","unstructured":"Chang ChCh, Lin ChJ (2009) LIBSVM: a library for support vector machines. http:\/\/www.csie.ntu.edu.tw\/~cjlin"},{"key":"9299_CR42","doi-asserted-by":"crossref","unstructured":"Chen CP, Blimes J, Kirchhoff K (2002) Low-resource noise-robust feature post-processing on AURORA 2.0. In: Proceedings of ICSLP, pp 2445\u20132448","DOI":"10.21437\/ICSLP.2002-637"},{"key":"9299_CR43","doi-asserted-by":"crossref","unstructured":"Kuo JW, Lo HY, Wang HM (2007) Improved HMM\/SVM methods for automatic phoneme segmentation. In: Proceedings of the tenth European conference on speech communication and technology (Interspeech2007-Eurospeech)","DOI":"10.21437\/Interspeech.2007-557"},{"key":"9299_CR44","doi-asserted-by":"crossref","first-page":"617","DOI":"10.1109\/TSA.2003.813579","volume":"11","author":"DT Toledano","year":"2003","unstructured":"Toledano DT, G\u00f3mez LAH, Grande LV (2003) Automatic phonetic segmentation. IEEE Trans Speech Audio Process 11:617\u2013625","journal-title":"IEEE Trans Speech Audio Process"},{"key":"9299_CR45","unstructured":"Toh M, Togneri R, Nordholm S (2005) Spectral entropy as speech features for speech recognition. In: Proceedings of postgraduate electrical engineering and computing symposium (PEECS) , pp 22\u201325"},{"key":"9299_CR46","unstructured":"Peeters G (2004) A large set of audio features for sound description (similarity and classification) in the CUIDADO project. Cuidado Project Report Ircam, pp 1\u201325"},{"key":"9299_CR47","first-page":"145","volume":"10","author":"ChY Lin","year":"2005","unstructured":"Lin ChY, Rager Jang JSh (2005) Automatic segmentation and labeling for Mandarin Chinese speech corpora for concatenation-based TTS. Comput Linguist Chin Lang Process 10:145\u2013166","journal-title":"Comput Linguist Chin Lang Process"},{"key":"9299_CR48","doi-asserted-by":"crossref","first-page":"2385","DOI":"10.1162\/089976600300014980","volume":"12","author":"G Buadat","year":"2000","unstructured":"Buadat G, Anouar F (2000) Generalized discriminant analysis using a kernel approach. J Neural Comput 12:2385\u20132404","journal-title":"J Neural Comput"},{"key":"9299_CR49","unstructured":"Zacharie DG, Pinto JP (2007) Keyword spotting on word lattices. Research Report, IDIAP Research Institute"},{"key":"9299_CR50","first-page":"305","volume":"17","author":"C Cortes","year":"2004","unstructured":"Cortes C, Mohri M (2004) Confidence intervals for the area under the ROC curve. Adv Neural Inf Process Syst 17:305\u2013312","journal-title":"Adv Neural Inf Process Syst"},{"key":"9299_CR51","unstructured":"Lori L, Kassel R, Stephanie S (1989) Speech database development: design and analysis of the acoustic-phonetic corpus. In: Proceedings of DARPA speech recognition workshop, vol 2, pp 161\u2013170"},{"key":"9299_CR52","doi-asserted-by":"crossref","first-page":"572","DOI":"10.1109\/TPAMI.2004.1273927","volume":"26","author":"Ch Liu","year":"2004","unstructured":"Liu Ch (2004) Gabor-based kernel PCA with fractional power polynomial models for face recognition. IEEE Trans Pattern Anal Mach Intell 26:572\u2013581","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9299_CR53","doi-asserted-by":"crossref","unstructured":"Rossius R, Zenker G, Ittner A, Dilger W (1998) A short note about the application of polynomial kernel with fractional degree in support vector learning. In: Lecture notes in computer science, pp 143\u2013148","DOI":"10.1007\/BFb0026684"},{"key":"9299_CR54","unstructured":"Tamimi H, Zell A (2004) Vision based localization of mobile robots using kernel approaches. In: Proceedings of the international conference on intelligent robots and systems (IROS 2004), pp 1896\u20131901"},{"key":"9299_CR55","doi-asserted-by":"crossref","unstructured":"Martin AF et al (1997) The DET curve in assessment of detection task performance. In: Proceedings of Eurospeech, vol 4, pp 1899\u20131903","DOI":"10.21437\/Eurospeech.1997-504"},{"key":"9299_CR56","volume-title":"Sensory evaluation of food: statistical methods and procedures","author":"M O\u2019Mahony","year":"1986","unstructured":"O\u2019Mahony M (1986) Sensory evaluation of food: statistical methods and procedures. CRC Press, Boca Raton"},{"key":"9299_CR57","unstructured":"Lomax RG (2007) Statistical concepts: a second course. Lawrence Erlbaum Associates, Mahwah"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-013-9299-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11063-013-9299-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-013-9299-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T03:50:29Z","timestamp":1688183429000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11063-013-9299-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,4,18]]},"references-count":57,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2014,4]]}},"alternative-id":["9299"],"URL":"https:\/\/doi.org\/10.1007\/s11063-013-9299-4","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"value":"1370-4621","type":"print"},{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,4,18]]}}}