{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T23:19:30Z","timestamp":1780615170767,"version":"3.54.1"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2014,1,24]],"date-time":"2014-01-24T00:00:00Z","timestamp":1390521600000},"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":[[2014,9]]},"DOI":"10.1007\/s10772-013-9221-5","type":"journal-article","created":{"date-parts":[[2014,1,23]],"date-time":"2014-01-23T12:55:25Z","timestamp":1390481725000},"page":"223-233","source":"Crossref","is-referenced-by-count":30,"title":["Hybrid continuous speech recognition systems by HMM, MLP and SVM: a comparative study"],"prefix":"10.1007","volume":"17","author":[{"given":"Elyes","family":"Zarrouk","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yassine","family":"Ben\u00a0Ayed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Faiez","family":"Gargouri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2014,1,24]]},"reference":[{"key":"9221_CR1","unstructured":"Abd-Arahman, H. (2008). Nutshell in science of tajweed ( ) (pp. 52\u201369) (in Arabic)."},{"key":"9221_CR2","unstructured":"Al-Diri, B., & Sharieh, A. (2002). A database for Arabic speech recognition ARABIC_DB (Technical Report). University of Jordan, Amman, Jordan."},{"issue":"2","key":"9221_CR3","first-page":"49","volume":"50","author":"B. Al-Diri","year":"2007","unstructured":"Al-Diri, B., Sharieh, A., & Qutiashat, M. (2007). A speech recognition model based on tri-phones for the Arabic language. Advances in Modelling and Analysis B: Signal Processing and Pattern Recognition, 50(2), 49\u201364. ISSN 1240-4543.","journal-title":"Advances in Modelling and Analysis B: Signal Processing and Pattern Recognition"},{"key":"9221_CR4","unstructured":"Al-Otaibi, F. (2001). Speaker-dependant continuous Arabic speech recognition. M.Sc. thesis, King Saud University."},{"key":"9221_CR5","volume-title":"IEEE international conference on acoustics, speech and signal processing (ICASSP)","author":"Y. Ben Ayed","year":"2003","unstructured":"Ben Ayed, Y., Fohr, D., Haton, J. P., & Chollet, G. (2003). Confidence measures for keyword spotting using support vector machines. In IEEE international conference on acoustics, speech and signal processing (ICASSP)."},{"key":"9221_CR6","volume-title":"Proceedings of the first workshop on text, speech, dialogue","author":"G. Bernadis","year":"1998","unstructured":"Bernadis, G., & Bourlard, H. (1998). Confidence measures in hybrid HMM\/ANN speech recognition. In Proceedings of the first workshop on text, speech, dialogue."},{"key":"9221_CR7","first-page":"617","volume-title":"Proceedings of the international conference on acoustics, speech and signal processing (ICASSP)","author":"J. M. Boite","year":"1994","unstructured":"Boite, J. M., Bourlard, H., D\u2019hoore, B., Accaino, S., & Vantieghem, J. (1994). Task independent and dependent training: performance comparison of HMM and hybrid HMM\/MLP approaches. In Proceedings of the international conference on acoustics, speech and signal processing (ICASSP) (Vol.\u00a01, pp. 617\u2013620)."},{"key":"9221_CR8","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. (1994). Connectionist speech recognition: a hybrid approach. Norwell, Boston: Kluwer Academic."},{"key":"9221_CR9","volume-title":"2nd information and communication technologies, ICTTA\u201906","author":"H. Bourouba","year":"2006","unstructured":"Bourouba, H., & Djemili, R. (2006). New hybrid system (supervised classifier\/HMM) for isolated Arabic speech recognition. In 2nd information and communication technologies, ICTTA\u201906."},{"key":"9221_CR10","volume-title":"Proceedings of the IEEE international conference on robotics and automation","author":"A. Castellani","year":"2004","unstructured":"Castellani, A., Botturi, D., Bicego, M., & Fiorini, P. (2004). Hybrid HMM\/SVM: model for the analysis and segmentation of teleoperation tasks. In Proceedings of the IEEE international conference on robotics and automation, New Orleans."},{"key":"9221_CR11","volume-title":"Proceedings of the 2008 fourth international conference on natural computation","author":"A.K. Chaudhuri De","year":"2008","unstructured":"Chaudhuri, A.K. De, & Chatterjee, D. (2008). A comparative study of kernels for the multi-class support vector machine. In: Proceedings of the 2008 fourth international conference on natural computation. Washington: IEEE Computer Society."},{"key":"9221_CR12","unstructured":"Connel, S. (1996). A comparison of hidden Markov model features for the recognition of cursive handwriting. Computer Science Department, Michigan State University, MS Thesis."},{"key":"9221_CR13","series-title":"Springer briefs in electrical computer engineering, search technology","first-page":"17","volume-title":"Cross-word modeling for Arabic speech recognition","author":"A. Dhia","year":"2012","unstructured":"Dhia, A., & Moustafa, E. (2012). Cross-word modeling for Arabic speech recognition. Springer briefs in electrical computer engineering, search technology (pp. 17\u201321). Berlin: Springer."},{"key":"9221_CR14","volume-title":"Eighth international symposium on natural language processing, SNLP","author":"M. Elmahdy","year":"2009","unstructured":"Elmahdy, M., Gruhn, R., et al. (2009). Modern standard Arabic based multilingual approach for dialectal Arabic speech recognition. In Eighth international symposium on natural language processing, SNLP."},{"key":"9221_CR15","unstructured":"Faria, A. (2007). An investigation of tandem MLP features for ASR. International Computer Science Institute, TR 07-003."},{"key":"9221_CR16","first-page":"2923","volume-title":"Proceedings of the ICSLP","author":"A. Ganapathiraju","year":"1998","unstructured":"Ganapathiraju, A., et al. (1998). Support vector machines for speech recognition. In Proceedings of the ICSLP, Sydney, Australia (pp. 2923\u20132926)."},{"key":"9221_CR17","volume-title":"ICASSP","author":"R. Gemello","year":"2006","unstructured":"Gemello, R., Mana, F., Scanzio, S., Laface, P., & De Mori, R. (2006). Adaptation of hybrid ANN\/HMM models using linear hidden transformations and conservative training. In ICASSP."},{"key":"9221_CR18","first-page":"329","volume-title":"Proceedings of Eurospeech\u201991","author":"H. Hermansky","year":"1991","unstructured":"Hermansky, H., & Cox, L. (1991). Perceptual linear predictive (PLP) analysis-resynthesis. In Proceedings of Eurospeech\u201991, Genova (pp. 329\u2013332)."},{"issue":"3\u20134","key":"9221_CR19","first-page":"133","volume":"9","author":"H. Hyassat","year":"2008","unstructured":"Hyassat, H., & Abu Zitar, R. (2008). Arabic speech recognition using SPHINX engine. International Journal of Speech Technology, 9(3\u20134), 133\u2013150.","journal-title":"International Journal of Speech Technology"},{"issue":"4","key":"9221_CR20","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1109\/PROC.1976.10159","volume":"64","author":"F. Jelinek","year":"1976","unstructured":"Jelinek, F. (1976). Continuous speech recognition by statistical methods. Proceedings of the IEEE, 64(4), 532\u2013556.","journal-title":"Proceedings of the IEEE"},{"key":"9221_CR21","unstructured":"Joachims, T. (1999). SVMLight: support vector machine. http:\/\/www-ai.informatik.unidortmund.de\/FORSCHUNG\/VERFAHREN\/SVM_LIGHT\/svm_light.eng.html , University of Dortmund, November 1999."},{"key":"9221_CR22","volume-title":"Les r\u00e9seaux de neurones: principes & d\u00e9finitions","author":"J. F. Jodouin","year":"1994","unstructured":"Jodouin, J. F. (1994). Les r\u00e9seaux de neurones: principes & d\u00e9finitions. Paris: Edition Hermes."},{"key":"9221_CR23","volume-title":"2010 IEEE international conference on acoustics speech and signal processing (ICASSP)","author":"H. J. Kuo","year":"2010","unstructured":"Kuo, H. J., Angu, L., et al. (2010). Morphological and syntactic features for Arabic speech recognition. In 2010 IEEE international conference on acoustics speech and signal processing (ICASSP)."},{"key":"9221_CR24","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-66286-7","volume-title":"Linear prediction of speech","author":"J. D. Markel","year":"1976","unstructured":"Markel, J. D., & Gray, A. H. Jr. (1976). Linear prediction of speech. Berlin: Springer."},{"key":"9221_CR25","volume-title":"Proceedings of IEEE international conference on acoustics, speech and signal processing, ICASSP 2006","author":"A. Messaoudi","year":"2006","unstructured":"Messaoudi, A., Gauvain, J. L., et al. (2006). Arabic broadcast news transcription using a one million word vocalized vocabulary. In Proceedings of IEEE international conference on acoustics, speech and signal processing, ICASSP 2006."},{"key":"9221_CR26","doi-asserted-by":"crossref","DOI":"10.5772\/93","volume-title":"Speech recognition technologies and applications","author":"F. Mihelic","year":"2008","unstructured":"Mihelic, F., & Zibert, J. (2008). Speech recognition technologies and applications. Vienna: I-TECH."},{"key":"9221_CR27","volume-title":"International conference on electrical, electronic and computer engineering, ICEEC\u201904","author":"M. Nofal","year":"2004","unstructured":"Nofal, M., Abdel, R. E., et al. (2004). The development of acoustic models for command and control Arabic speech recognition system. In International conference on electrical, electronic and computer engineering, ICEEC\u201904."},{"issue":"9","key":"9221_CR28","doi-asserted-by":"crossref","first-page":"1272","DOI":"10.1109\/JPROC.2003.817117","volume":"91","author":"D. O\u2019Shaughnessy","year":"2003","unstructured":"O\u2019Shaughnessy, D. (2003). Interacting with computers by voice automatic speech recognitions and synthesis. Proceedings of the IEEE, 91(9), 1272\u20131300.","journal-title":"Proceedings of the IEEE"},{"key":"9221_CR29","volume-title":"IEEE international conference on acoustics, speech and signal processing, ICASSP2009","author":"J. Park","year":"2009","unstructured":"Park, J., Diehl, F., et al. (2009). Training and adapting MLP features for Arabic speech recognition. In IEEE international conference on acoustics, speech and signal processing, ICASSP2009."},{"key":"9221_CR30","volume-title":"Fundamentals of speech recognition","author":"L.-R. Rabiner","year":"1993","unstructured":"Rabiner, L.-R., & Juang, B.-H. (1993). Fundamentals of speech recognition. New York: Prentice-Hall."},{"issue":"4","key":"9221_CR31","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1007\/s10772-011-9108-2","volume":"14","author":"K. A. Rajesh","year":"2011","unstructured":"Rajesh, K. A., & Mayank, D. (2011). Acoustic modeling problem for automatic speech recognition system: conventional methods (Part I). International Journal of Speech Technology, 14(4), 297\u2013308.","journal-title":"International Journal of Speech Technology"},{"key":"9221_CR32","volume-title":"2010 IEEE international conference on acoustics speech and signal processing (ICASSP)","author":"G. Saon","year":"2010","unstructured":"Saon, G., Soltau, H., et al. (2010). The IBM 2008 GALE Arabic speech transcription system. In 2010 IEEE international conference on acoustics speech and signal processing (ICASSP)."},{"key":"9221_CR33","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1109\/ICASSP.1980.1171037","volume-title":"Proceedings IEEE international conference on acoustics, speech, and signal processing","author":"R. Schwartz","year":"1980","unstructured":"Schwartz, R., Klovstad, J., Makhoul, J., & Sorensen, J. (1980). A preliminary design of a phonetic vocoder based on a diphone model. In Proceedings IEEE international conference on acoustics, speech, and signal processing (pp. 32\u201335)."},{"issue":"1","key":"9221_CR34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.aci.2010.03.001","volume":"9","author":"S.-A. Selouani","year":"2011","unstructured":"Selouani, S.-A., & Alotaibi, Y. A. (2011). Adaptation of foreign accented speakers in native Arabic ASR systems. Applied Computer Information, 9(1), 1\u201310.","journal-title":"Applied Computer Information"},{"key":"9221_CR35","first-page":"371","volume-title":"7th international multi topic conference, INMIC 2003","author":"M. Shoaib","year":"2003","unstructured":"Shoaib, M., Rasheed, F., Akhtar, J., Awais, M., Masud, S., & Shamail, S. (2003). A novel approach to increase the robustness of speaker independent Arabic speech recognition. In 7th international multi topic conference, INMIC 2003 (pp. 371\u2013376)."},{"key":"9221_CR36","volume-title":"IEEE international conference on acoustics, speech and signal processing, ICASSP2007","author":"H. Soltau","year":"2007","unstructured":"Soltau, H., Saon, G., et al. (2007). The IBM 2006 gale Arabic ASR system. In IEEE international conference on acoustics, speech and signal processing, ICASSP2007."},{"key":"9221_CR37","unstructured":"Steve, Y., Gunnar, E., Mark, G., Thomas, H., Dan, K., Liu Gareth M, X. A., Julian, O., Dave, O., Dan, P., Valtcho, V., & Phil, W. (2006). The HTK book (for HTK Version 3.4) (pp.\u00a0294\u2013297). Cambridge University Engineering Department."},{"key":"9221_CR38","volume-title":"Estimation of dependences based an empirical data","author":"V. Vapnik","year":"1979","unstructured":"Vapnik, V. (1979). Estimation of dependences based an empirical data. Moscow: Nauka. English translation, Springer, New York (1979)."},{"key":"9221_CR39","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. (1995). The nature of statistical learning theory. New York: Springer."},{"key":"9221_CR40","first-page":"1089","volume-title":"Proceedings of ICASSP","author":"B. Xiang","year":"2006","unstructured":"Xiang, B., Nguyen, K., Nguyen, L., Schwartz, R., & Makhoul, J. (2006). Morphological decomposition for Arabic broadcast news transcription. In Proceedings of ICASSP, Toulouse (Vol. I, pp.\u00a01089\u20131092)."},{"key":"9221_CR41","first-page":"183","volume-title":"Proceedings of SPED conference","author":"E. Zarrouk","year":"2011","unstructured":"Zarrouk, E., & Ben Ayed, Y. (2011). Automatic speech recognition with hybrid models. In Proceedings of SPED conference (pp.\u00a0183\u2013188)."},{"key":"9221_CR42","unstructured":"Zarrouk, E., & Ben Ayed, Y. (2012, in press). Hybrid SVM\/HMM model for the Arab phonemes recognition. The International Arab Journal of Information Technology. Paper ID:5665."},{"key":"9221_CR43","volume-title":"10th international multi-conference on systems, signals & devices (SSD)","author":"E. Zarrouk","year":"2013","unstructured":"Zarrouk, E., Ben Ayed, Y., & Gargouri, F. (2013). Hybrid SVM\/HMM model for the recognition of Arabic triphones-based continuous speech. In 10th international multi-conference on systems, signals & devices (SSD), Tunisia."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-013-9221-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-013-9221-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-013-9221-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,31]],"date-time":"2019-05-31T00:02:46Z","timestamp":1559260966000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-013-9221-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,1,24]]},"references-count":43,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2014,9]]}},"alternative-id":["9221"],"URL":"https:\/\/doi.org\/10.1007\/s10772-013-9221-5","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,1,24]]}}}