{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T11:56:42Z","timestamp":1762430202679,"version":"3.33.0"},"publisher-location":"Berlin, Heidelberg","reference-count":54,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540715030"},{"type":"electronic","value":"9783540715054"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-71505-4_11","type":"book-chapter","created":{"date-parts":[[2007,5,23]],"date-time":"2007-05-23T21:29:56Z","timestamp":1179955796000},"page":"190-216","source":"Crossref","is-referenced-by-count":23,"title":["SVMs for Automatic Speech Recognition: A Survey"],"prefix":"10.1007","author":[{"given":"R.","family":"Solera-Ure\u00f1a","sequence":"first","affiliation":[]},{"given":"J.","family":"Padrell-Sendra","sequence":"additional","affiliation":[]},{"given":"D.","family":"Mart\u00edn-Iglesias","sequence":"additional","affiliation":[]},{"given":"A.","family":"Gallardo-Antol\u00edn","sequence":"additional","affiliation":[]},{"given":"C.","family":"Pel\u00e1ez-Moreno","sequence":"additional","affiliation":[]},{"given":"F.","family":"D\u00edaz-de-Mar\u00eda","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Sakoe, H., Isotani, R., Yoshida, K., Iso, K., Watanabe, T.: Speaker-Independent Word Recognition using Dynamic Programming Neural Networks. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), Glasgow, Scotland, pp. 439\u2013442 (1989)","DOI":"10.1109\/ICASSP.1989.266355"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Iso, K., Watanabe, T.: Speaker-Independent Word Recognition using a Neural Prediction Model. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), Alburquerque, New Mexico, USA, pp. 441\u2013444 (1990)","DOI":"10.1109\/ICASSP.1990.115744"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Tebelskis, J., Waibel, A., Petek, B., Schmidbauer, O.: Continuous Speech Recognition using Predictive Neural Networks. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, Canada, pp. 61\u201364 (1991)","DOI":"10.1109\/ICASSP.1991.150278"},{"key":"11_CR4","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4615-3210-1","volume-title":"Connectionist speech recognition: a hybrid approach","author":"H. Bourlard","year":"1994","unstructured":"Bourlard, H., Morgan, N.: Connectionist speech recognition: a hybrid approach. Kluwer Academic Publishers, Dordrecht (1994)"},{"key":"11_CR5","volume-title":"Learning with kernels","author":"B. Schlkopf","year":"2002","unstructured":"Schlkopf, B., Smola, A.: Learning with kernels. MIT Press, Cambridge (2002)"},{"key":"11_CR6","volume-title":"Statistical Learning Theory","author":"V. Vapnik","year":"1998","unstructured":"Vapnik, V.: Statistical Learning Theory. Wiley, Chichester (1998)"},{"key":"11_CR7","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-2440-0","volume-title":"The Nature of Statistical Learning Theory","author":"V. Vapnik","year":"1995","unstructured":"Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995)"},{"key":"11_CR8","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1109\/29.21701","volume":"37","author":"A. Waibel","year":"1989","unstructured":"Waibel, A., Hanazawa, T., Hinton, G., Shikano, K., Lang, K.: Phoneme recognition using time-delay neural networks. IEEE Transactions on Acoustics, Speech and Signal Processing\u00a037, 328\u2013339 (1989)","journal-title":"IEEE Transactions on Acoustics, Speech and Signal Processing"},{"key":"11_CR9","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1016\/0885-2308(91)90010-N","volume":"5","author":"T. Robinson","year":"1991","unstructured":"Robinson, T., Fallside, F.: A recurrent error propagation network speech recognition system. Computer, Speech and Language\u00a05, 259\u2013274 (1991)","journal-title":"Computer, Speech and Language"},{"key":"11_CR10","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/S0925-2312(00)00308-8","volume":"37","author":"E. Trentin","year":"2001","unstructured":"Trentin, E., Gori, M.: A survey of hybrid ann\/hmm models for automatic speech recognition. Neurocomputing\u00a037, 91\u2013126 (2001)","journal-title":"Neurocomputing"},{"key":"11_CR11","doi-asserted-by":"publisher","first-page":"893","DOI":"10.1109\/72.286885","volume":"4","author":"H. Bourlard","year":"1993","unstructured":"Bourlard, H., Morgan, N.: Continuous speech recognition by connectionist statistical methods. IEEE Transactions on Neural Networks\u00a04, 893\u2013909 (1993)","journal-title":"IEEE Transactions on Neural Networks"},{"key":"11_CR12","first-page":"159","volume-title":"Automatic Speech and Speaker Recognition - Advanced Topics","author":"T. Robinson","year":"1995","unstructured":"Robinson, T., Hochberg, M., Renals, S.: The Use of Recurrent Neural Networks in Continuous Speech Recognition. In: Automatic Speech and Speaker Recognition - Advanced Topics, pp. 159\u2013184. Kluwer Academic Publishers, Norwell (1995)"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Reichl, W., Ruske, G.: A hybrid rbf-hmm system for continuous speech recognition. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), Detroit, MI, USA, pp. 3335\u20133338 (1995)","DOI":"10.1109\/ICASSP.1995.479699"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Ellis, D., Singh, R., Sivadas, S.: Tandem-acoustic modeling in large-vocabulary recognition. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), Salt Lake City, Utah, USA, pp. 517\u2013520 (2001)","DOI":"10.1109\/ICASSP.2001.940881"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Boser, B.E., Guyon, I., Vapnik, V.: A training algorithm for optimal margin classifiers. In: Computational Learning Theory, pp. 144\u2013152 (1992)","DOI":"10.1145\/130385.130401"},{"issue":"3","key":"11_CR16","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1109\/MSP.2004.1296543","volume":"21","author":"F. P\u00e9rez-Cruz","year":"2004","unstructured":"P\u00e9rez-Cruz, F., Bousquet, O.: Kernel Methods and Their Potential Use in Signal Processing. IEEE Signal Processing Magazine\u00a021(3), 57\u201365 (2004)","journal-title":"IEEE Signal Processing Magazine"},{"key":"11_CR17","volume-title":"Practical Methods of Optimization","author":"R. Fletcher","year":"1987","unstructured":"Fletcher, R.: Practical Methods of Optimization. Wiley-Interscience, New York (1987)"},{"issue":"5","key":"11_CR18","doi-asserted-by":"publisher","first-page":"1047","DOI":"10.1109\/72.950134","volume":"12","author":"A. Navia-V\u00e1zquez","year":"2001","unstructured":"Navia-V\u00e1zquez, A., P\u00e9rez-Cruz, F., Art\u00e9s-Rodr\u00edguez, A., Figueiras-Vidal, A.R.: Weighted Least Squares Training of Support Vector Classifiers leading to Compact and Adaptive Schemes. IEEE Transactions on Neural Networks\u00a012(5), 1047\u20131059 (2001)","journal-title":"IEEE Transactions on Neural Networks"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Fine, S., Navratil, J., Gopinath, R.A.: A hybrid gmm\/svm approach to speaker identification. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 1, Salt Lake City, Utah, USA, pp. 417\u2013420 (2001)","DOI":"10.1109\/ICASSP.2001.940856"},{"key":"11_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1007\/3-540-44989-2_53","volume-title":"Artificial Neural Networks and Neural Information Processing - ICANN\/ICONIP 2003","author":"Q. Le","year":"2003","unstructured":"Le, Q., Bengio, S.: Client Dependent GMM-SVM Models for Speaker Verification. In: Kaynak, O., Alpayd\u0131n, E., Oja, E., Xu, L. (eds.) ICANN 2003 and ICONIP 2003. LNCS, vol.\u00a02714, pp. 443\u2013451. Springer, Heidelberg (2003)"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Ma, C., Randolph, M.A., Drish, J.: A support vector machines-based rejection technique for speech recognition. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 1, Salt Lake City, Utah, USA, pp. 381\u2013384 (2001)","DOI":"10.1109\/ICASSP.2001.940847"},{"issue":"2","key":"11_CR22","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1109\/72.991427","volume":"13","author":"C.W. Hsu","year":"2002","unstructured":"Hsu, C.W., Lin, C.J.: A Comparison of Methods for Multi-class Support Vector Machines. IEEE Transactions on Neural Networks\u00a013(2), 415\u2013425 (2002)","journal-title":"IEEE Transactions on Neural Networks"},{"key":"11_CR23","doi-asserted-by":"publisher","first-page":"2348","DOI":"10.1109\/TSP.2004.831018","volume":"52","author":"A. Ganapathiraju","year":"2004","unstructured":"Ganapathiraju, A., Hamaker, J.E., Picone, J.: Applications of support vector machines to speech recognition. IEEE Transactions on Signal Processing\u00a052, 2348\u20132355 (2004)","journal-title":"IEEE Transactions on Signal Processing"},{"key":"11_CR24","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1142\/S0218488501001253","volume":"9","author":"N. Thubthong","year":"2001","unstructured":"Thubthong, N., Kijsirikul, B.: Support vector machines for thai phoneme recognition. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems\u00a09, 803\u2013813 (2001)","journal-title":"International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Clarkson, P., Moreno, P.J.: On the use of support vector machines for phonetic classification. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 2, Phoenix, Arizona, USA, pp. 585\u2013588 (1999)","DOI":"10.1109\/ICASSP.1999.759734"},{"key":"11_CR26","unstructured":"Sekhar, C., Lee, W.F., Takeda, K., Itakura, F.: Acoustic modelling of subword units using support vector machines. In: Workshop on spoken language processing, Mumbai, India (2003)"},{"key":"11_CR27","volume-title":"HTK-Hidden Markov Model Toolkit (ver 2.1)","author":"S. Young","year":"1995","unstructured":"Young, S.: HTK-Hidden Markov Model Toolkit (ver 2.1). Cambridge University Press, Cambridge (1995)"},{"key":"11_CR28","unstructured":"Garc\u00eda-Cabellos, J.M., Pel\u00e1ez-Moreno, C., Gallardo-Antol\u00edn, A., P\u00e9rez-Cruz, F., D\u00edaz-de-Mar\u00eda, F.: SVM Classifiers for ASR: A Discusion about Parameterization. In: Proceedings of EUSIPCO 2004, Wien, Austria, pp. 2067\u20132070 (2004)"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Ech-Cherif, A., Kohili, M., Benyettou, A., Benyettou, M.: Lagrangian support vector machines for phoneme classification. In: Proceedings of the 9th International Conference on Neural Information Processing (ICONIP \u201902), vol. 5, Singapore, pp. 2507\u20132511 (2002)","DOI":"10.1109\/ICONIP.2002.1201946"},{"key":"11_CR30","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/11613107_22","volume-title":"Nonlinear Analyses and Algorithms for Speech Processing","author":"D. Mart\u00edn-Iglesias","year":"2006","unstructured":"Mart\u00edn-Iglesias, D., Bernal-Chaves, J., Pel\u00e1ez-Moreno, C., Gallardo-Antol\u00edn, A., D\u00edaz-de-Mar\u00eda, F.: A Speech Recognizer Based on Multiclass SVMs with HMM-Guided Segmentation. In: Faundez-Zanuy, M., Janer, L., Esposito, A., Satue-Villar, A., Roure, J., Espinosa-Duro, V. (eds.) NOLISP 2005. LNCS (LNAI), vol.\u00a03817, pp. 257\u2013266. Springer, Heidelberg (2006)"},{"key":"11_CR31","doi-asserted-by":"crossref","unstructured":"Solera-Ure\u00f1a, R., Mart\u00edn-Iglesias, D., Gallardo-Antol\u00edn, A., Pel\u00e1ez-Moreno, C., D\u00edaz-de-Mar\u00eda, F.: Robust ASR using Support Vector Machines. Speech Communication, Elsevier, submitted (2006)","DOI":"10.1016\/j.specom.2007.01.013"},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Gangashetty, S.V., Sekhar, C., Yegnanarayana, B.: Combining evidence from multiple classifiers for recognition of consonant-vowel units of speech in multiple languages. In: Proceedings of the International Conference on Intelligent Sensing and Information Processing, Chennai, India, pp. 387\u2013391 (2005)","DOI":"10.1109\/ICISIP.2005.1529482"},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Shimodaira, H., Noma, K.I., Nakai, M., Sagayama, S.: Support vector machine with dynamic time-alignment kernel for speech recognition. In: Proceedings of Eurospeech, Aalborg, Denmark, pp. 1841\u20131844 (2001)","DOI":"10.21437\/Eurospeech.2001-435"},{"key":"11_CR34","first-page":"921","volume-title":"Advances in Neural Information Processing Systems 14, vol. 2","author":"H. Shimodaira","year":"2002","unstructured":"Shimodaira, H., Noma, K., Nakai, M.: Dynamic Time-Alignment Kernel in Support Vector Machine. In: Advances in Neural Information Processing Systems 14, vol. 2, pp. 921\u2013928. MIT Press, Cambridge (2002)"},{"issue":"6","key":"11_CR35","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1109\/TASSP.1978.1163164","volume":"26","author":"L.R. Rabiner","year":"1978","unstructured":"Rabiner, L.R., Rosenberg, A.E., Levinson, S.E.: Considerations in Dynamic Time Warping Algorithms for Discrete Word Recognition. IEEE Transactions on Acoustics, Speech and Signal Processing\u00a026(6), 575\u2013582 (1978)","journal-title":"IEEE Transactions on Acoustics, Speech and Signal Processing"},{"key":"11_CR36","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/S0885-2308(03)00006-8","volume":"17","author":"J.R. Glass","year":"2003","unstructured":"Glass, J.R.: A probabilistic framework for segment-based speech recognition. Computer Speech and Language\u00a017, 137\u2013152 (2003)","journal-title":"Computer Speech and Language"},{"key":"11_CR37","unstructured":"Jaakkola, T., Haussler, D.: Exploiting generative models in discriminative classifiers. Technical report, Dept. of Computer Science, Univ. of California (1998)"},{"key":"11_CR38","doi-asserted-by":"crossref","unstructured":"Smith, N.D., Gales, M.J.F.: Using SVMs and discriminative models for speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 1, Orlando, Florida, USA, pp. 77\u201380 (2002)","DOI":"10.1109\/ICASSP.2002.1005680"},{"key":"11_CR39","first-page":"1197","volume-title":"Advances in Neural Information Processing Systems 14","author":"N.D. Smith","year":"2002","unstructured":"Smith, N.D., Gales, M.J.F.: Speech recognition using SVMs. In: Advances in Neural Information Processing Systems 14, pp. 1197\u20131204. MIT Press, Cambridge (2002)"},{"key":"11_CR40","doi-asserted-by":"crossref","unstructured":"Smith, N.D., Niranjan, M.: Data-dependent Kernels in SVM Classification of Speech Patterns. In: Proceedings of the International Conference on Spoken Language Processing (ICSLP), vol. 1, Beijing, China, pp. 297\u2013300 (2000)","DOI":"10.21437\/ICSLP.2000-74"},{"key":"11_CR41","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1109\/TSA.2004.841042","volume":"13","author":"V. Wan","year":"2005","unstructured":"Wan, V., Renals, S.: Speaker verification using sequence discriminant support vector machines. IEEE Transactions on Speech and Audio Processing\u00a013, 203\u2013210 (2005)","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"11_CR42","doi-asserted-by":"crossref","unstructured":"Ganapathiraju, A., Hamaker, J., Picone, J.: Hybrid SVM\/HMM Architectures for Speech Recognition. In: Proceedings of the 2000 Speech Transcription Workshop, vol. 4, Maryland, USA, May 2000, pp. 504\u2013507 (2000)","DOI":"10.21437\/ICSLP.2000-859"},{"key":"11_CR43","unstructured":"Padrell-Sendra, J., Mart\u00edn-Iglesias, D., D\u00edaz-de-Mar\u00eda, F.: Support vector machines for continuous speech recognition. In: Proceedings of the 14th European Signal Processing Conference, Florence, Italy (2006)"},{"key":"11_CR44","unstructured":"Young, S.J., Russell, N.H., Thornton, J.H.S.: Token Passing: a Conceptual Model for Connected Speech Recognition Systems. Technical report, CUED Cambridge University (1989)"},{"key":"11_CR45","doi-asserted-by":"crossref","unstructured":"Cosi, P.: Hybrid HMM-NN architectures for connected digit recognition. In: Proceedings of the International Joint Conference on Neural Networks, vol.\u00a05, pp. 85\u201390 (2000)","DOI":"10.1109\/IJCNN.2000.861439"},{"key":"11_CR46","doi-asserted-by":"crossref","unstructured":"Juneja, A., Espy-Wilson, C.: Segmentation of continuous speech using acoustic-phonetic parameters and statistical learning. In: Proceedings of the 9th International Conference on Neural Information Processing (ICONIP \u201902), vol.\u00a02, pp. 726\u2013730 (2002)","DOI":"10.1109\/ICONIP.2002.1198153"},{"key":"11_CR47","unstructured":"Chang, C.-C., Lin, C.-J.: LIBSVM: a library for support vector machines (2004)"},{"key":"11_CR48","first-page":"185","volume-title":"Advances in Kernel Methods: Support Vector Learning","author":"J.C. Platt","year":"1999","unstructured":"Platt, J.C.: Fast Training of Support Vector Machines Using Sequential Minimal Optimization. In: Advances in Kernel Methods: Support Vector Learning, pp. 185\u2013208. MIT Press, Cambridge (1999)"},{"key":"11_CR49","first-page":"61","volume-title":"Advances in Large Margin Classifiers","author":"J.C. Platt","year":"1999","unstructured":"Platt, J.C.: Probabilities for SV Machines. In: Advances in Large Margin Classifiers, pp. 61\u201374. MIT Press, Cambridge (1999)"},{"key":"11_CR50","first-page":"975","volume":"5","author":"T.F. Wu","year":"2004","unstructured":"Wu, T.F., Lin, C.J., Weng, R.C.: Probability estimates for multi-class classification by pairwise coupling. The Journal of Machine Learning Research\u00a05, 975\u20131005 (2004)","journal-title":"The Journal of Machine Learning Research"},{"key":"11_CR51","unstructured":"Burges, C.J.C.: Simplified support vector decision rules. In: Proceedings of the Thirteenth International Conference on Machine Learning, Bari, Italy, pp. 71\u201377 (1996)"},{"key":"11_CR52","doi-asserted-by":"crossref","unstructured":"Osuna, E., Freund, R., Girosi, F.: An improved training algorithm for support vector machines. In: IEEE Workshop on Neural Networks for Signal Processing, Amelia Island, Florida, USA, pp. 276\u2013285 (1997)","DOI":"10.1109\/NNSP.1997.622408"},{"key":"11_CR53","unstructured":"Guti\u00e9rrez, D., Parrado, E., Navia, A.: Mega-GSVC: Training SVMs with Millions of Data. In: Proceedings of the Learning\u201904 International Conference (2004)"},{"key":"11_CR54","doi-asserted-by":"publisher","first-page":"1479","DOI":"10.1016\/S0031-3203(02)00351-5","volume":"36","author":"E. Parrado","year":"2003","unstructured":"Parrado, E., Arenas, J., Mora, I., Figueiras, A., Navia, A.: Growing Support Vector Classifiers with Controlled Complexity. Pattern Recognition\u00a036, 1479\u20131488 (2003)","journal-title":"Pattern Recognition"}],"container-title":["Lecture Notes in Computer Science","Progress in Nonlinear Speech Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-71505-4_11.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T15:42:19Z","timestamp":1737042139000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-71505-4_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540715030","9783540715054"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-71505-4_11","relation":{},"subject":[]}}