{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T03:48:29Z","timestamp":1773546509360,"version":"3.50.1"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2018,7,16]],"date-time":"2018-07-16T00:00:00Z","timestamp":1531699200000},"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":[[2018,9]]},"DOI":"10.1007\/s10772-018-9535-4","type":"journal-article","created":{"date-parts":[[2018,7,16]],"date-time":"2018-07-16T08:22:47Z","timestamp":1531729367000},"page":"689-704","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["A new hybrid framework based on Hidden Markov models and K-nearest neighbors for speech recognition"],"prefix":"10.1007","volume":"21","author":[{"given":"Samira","family":"Hazmoune","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fateh","family":"Bougamouza","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Smaine","family":"Mazouzi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed","family":"Benmohammed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,7,16]]},"reference":[{"key":"9535_CR1","doi-asserted-by":"crossref","unstructured":"Abdel-Hamid, O., Mohamed, A. R., Jiang, H., & Penn, G. (2012). Applying convolutional neural networks concepts to hybrid NN-HMM model for speech recognition. In the IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp.\u00a04277\u20134280). Kyoto: IEEE","DOI":"10.1109\/ICASSP.2012.6288864"},{"key":"9535_CR3","unstructured":"AlKhateeb, J. H., Khelifi, F., Jiang, J., & Ipson, S. S. (2009). A new approach for off-line handwritten Arabic word recognition using KNN classifier. In IEEE international conference on signal and image processing applications (ICSIPA) (pp.\u00a0191\u2013194). Kuala Lumpur: IEEE."},{"key":"9535_CR4","unstructured":"Al-Qatab, B. A., & Ainon, R. N. (2010). Arabic speech recognition using hidden Markov model toolkit (HTK). In International symposium in information technology (ITSim) (Vol.\u00a02, pp.\u00a0557\u2013562). Kuala Lumpur: IEEE."},{"key":"9535_CR5","unstructured":"Biem, A. (2003). A model selection criterion for classification: Application to hmm topology optimization. In Seventh international conference on document analysis and recognition (pp.\u00a0104\u2013108). Edinburgh: IEEE."},{"key":"9535_CR6","unstructured":"Bougamouza, F., Hazmoune, S., & Benmohammed, M. (2016). Using Mel Frequency Cepstral Coefficient method for online Arabic characters handwriting recognition. In 5th international conference on multimedia computing and systems (ICMCS) (pp.\u00a087\u201392). Rabat: IEEE."},{"issue":"9","key":"9535_CR7","doi-asserted-by":"publisher","first-page":"3544","DOI":"10.1016\/j.patcog.2012.02.034","volume":"45","author":"PR Cavalin","year":"2012","unstructured":"Cavalin, P. R., Sabourin, R., & Suen, C. Y. (2012). LoGID: An adaptive framework combining local and global incremental learning for dynamic selection of ensembles of HMMs. Pattern Recognition, 45(9), 3544\u20133556.","journal-title":"Pattern Recognition"},{"key":"9535_CR8","doi-asserted-by":"crossref","unstructured":"Chebotar, Y., & Waters, A. (2016). Distilling knowledge from ensembles of neural networks for speech recognition. In Interspeech, San Francisco (pp.\u00a03439\u20133443).","DOI":"10.21437\/Interspeech.2016-1190"},{"key":"9535_CR9","unstructured":"Clarkson, P., & Moreno, P. J. (1999). On the use of support vector machines for phonetic classification. In IEEE international conference on acoustics, speech, and signal processing (Vol.\u00a02, pp.\u00a0585\u2013588). Phoenix: IEEE."},{"issue":"1","key":"9535_CR10","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1016\/S1077-3142(03)00081-X","volume":"91","author":"I Cohen","year":"2003","unstructured":"Cohen, I., Sebe, N., Garg, A., Chen, L. S., & Huang, T. S. (2003). Facial expression recognition from video sequences: temporal and static modeling. Computer Vision and Image Understanding, 91(1), 160\u2013187.","journal-title":"Computer Vision and Image Understanding"},{"key":"9535_CR11","doi-asserted-by":"crossref","unstructured":"Deselaers, T., Heigold, G., & Ney, H. (2007). Speech recognition with state-based nearest neighbour classifiers. In Interspeech-2007, Antwerp (pp.\u00a02093\u20132096.","DOI":"10.21437\/Interspeech.2007-566"},{"key":"9535_CR12","unstructured":"Dhanashri, D., & Dhonde, S. B. (2017). Isolated word speech recognition system using deep neural networks. In Proceedings of the international conference on data engineering and communication technology (pp.\u00a09\u201317). Singapore: Springer."},{"issue":"23","key":"9535_CR13","doi-asserted-by":"publisher","first-page":"15537","DOI":"10.1007\/s11042-015-2505-9","volume":"75","author":"J Ding","year":"2016","unstructured":"Ding, J., & Chang, C. W. (2016). An adaptive hidden Markov model-based gesture recognition approach using Kinect to simplify large-scale video data processing for humanoid robot imitation. Multimedia Tools and Applications, 75(23), 15537\u201315551.","journal-title":"Multimedia Tools and Applications"},{"issue":"60","key":"9535_CR14","first-page":"606","volume":"13","author":"Z En-Naimani","year":"2014","unstructured":"En-Naimani, Z., Lazaar, M., & Ettaouil, M. (2014). Hybrid system of optimal self organizing maps and hidden Markov model for Arabic digits recognition. WSEAS Transactions on Systems, 13(60), 606\u2013616.","journal-title":"WSEAS Transactions on Systems"},{"key":"9535_CR15","doi-asserted-by":"crossref","unstructured":"Fix, E., & Hodges, J. L. (1951). Discriminatory analysis, nonparametric discrimination: Consistency properties, Technical Report 4, USAF School of Aviation Medicine, Randolph Field, Texas.","DOI":"10.1037\/e471672008-001"},{"key":"9535_CR16","doi-asserted-by":"crossref","unstructured":"Ganapathiraju, A., Hamaker, J., & Picone, J. (2000). Hybrid SVM\/HMM architectures for speech recognition. In Sixth international conference on spoken language processing, Beijing (Vol.\u00a04, pp.\u00a0504\u2013507).","DOI":"10.21437\/ICSLP.2000-859"},{"issue":"8","key":"9535_CR17","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. (2004). Applications of support vector machines to speech recognition. IEEE Transactions on Signal Processing, 52(8), 2348\u20132355.","journal-title":"IEEE Transactions on Signal Processing"},{"key":"9535_CR18","unstructured":"Geiger, J., Schenk, J., Wallhoff, F., & Rigoll, G. (2010). Optimizing the number of states for HMM-based on-line handwritten whiteboard recognition. In International conference on frontiers in handwriting recognition (ICFHR) (pp.\u00a0107\u2013112). Kolkata: IEEE."},{"key":"9535_CR19","unstructured":"Gunter, S., & Bunke, H. (2003). Optimizing the number of states, training iterations and Gaussians in an HMM-based handwritten word recognizer. In Seventh international conference on document analysis and recognition, (pp.\u00a0472\u2013476). Edinburgh: IEEE."},{"key":"9535_CR20","unstructured":"Hai, N. T., Van Thuyen, N., Mai, T. T., & Van Toi, V. (2015). MFCC-DTW algorithm for speech recognition in an intelligent wheelchair. In 5th international conference on biomedical engineering in Vietnam (pp.\u00a0417\u2013421). Cham: Springer."},{"key":"9535_CR21","doi-asserted-by":"crossref","unstructured":"Hammami, N., & Bedda, M. (2010). Improved tree model for Arabic speech recognition. In 3rd IEEE international conference on computer science and information technology (ICCSIT) (Vol.\u00a05, pp.\u00a0521\u2013526). IEEE.","DOI":"10.1109\/ICCSIT.2010.5563892"},{"key":"9535_CR22","unstructured":"Hammami, N., Bedda, M., & Farah, N. (2011). HMM parameters estimation based on cross-validation for Spoken Arabic Digits recognition. In International conference on communications, computing and control applications (CCCA) (pp.\u00a01\u20134). Hammamet: IEEE."},{"key":"9535_CR23","unstructured":"Hammami, N., Bedda, M., Farah, N., & Lakehal-Ayat, R. O. (2013). Spoken Arabic Digits recognition based on (GMM) for e-Quran voice browsing: Application for blind category. In Taibah University international conference on advances in information technology for the Holy Quran and its sciences (32519), (pp.\u00a0123\u2013127). Medina: IEEE."},{"key":"9535_CR24","doi-asserted-by":"crossref","unstructured":"Hammami, N., Bedda, M., & Nadir, F. (2012). The second-order derivatives of MFCC for improving spoken Arabic digits recognition using tree distributions approximation model and HMMs. In International conference on communications and information technology (ICCIT), (pp.\u00a01\u20135). IEEE.","DOI":"10.1109\/ICCITechnol.2012.6285769"},{"key":"9535_CR25","doi-asserted-by":"crossref","unstructured":"Hazmoune, S., Bougamouza, F., Mazouzi, S., & Benmohammed, M. (2013a). A novel speech recognition approach based on multiple modeling by hidden Markov models. In International Conference on Computer Applications Technology (ICCAT), 2013 (pp.\u00a01\u20136). Sousse: IEEE.","DOI":"10.1109\/ICCAT.2013.6522028"},{"issue":"1","key":"9535_CR26","first-page":"38","volume":"4","author":"S Hazmoune","year":"2013","unstructured":"Hazmoune, S., Bougamouza, F., Mazouzi, S., & Benmohammed, M. (2013b). Contributions to HMM-based speech recognition systems. International Journal of Computational Linguistics Research, 4(1), 38\u201347.","journal-title":"International Journal of Computational Linguistics Research"},{"key":"9535_CR27","unstructured":"Jiang, Z., Ding, X., Peng, L., & Liu, C. (2012). Analyzing the information entropy of states to optimize the number of states in an HMM-based off-line handwritten Arabic word recognizer. In 21st International Conference on Pattern Recognition (ICPR) (pp.\u00a0697\u2013700). Istanbul: IEEE."},{"issue":"4","key":"9535_CR28","doi-asserted-by":"publisher","first-page":"937","DOI":"10.1007\/s10772-017-9456-7","volume":"20","author":"MO Khelifa","year":"2017","unstructured":"Khelifa, M. O., Elhadj, Y. M., Abdellah, Y., & Belkasmi, M. (2017). Constructing accurate and robust HMM\/GMM models for an Arabic speech recognition system. International Journal of Speech Technology, 20(4), 937\u2013949.","journal-title":"International Journal of Speech Technology"},{"issue":"2","key":"9535_CR29","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1016\/S0031-3203(99)00226-5","volume":"34","author":"S Kwong","year":"2001","unstructured":"Kwong, S., Chau, C. W., Man, K. F., & Tang, K. S. (2001). Optimisation of HMM topology and its model parameters by genetic algorithms. Pattern Recognition, 34(2), 509\u2013522.","journal-title":"Pattern Recognition"},{"issue":"10","key":"9535_CR30","doi-asserted-by":"publisher","first-page":"961","DOI":"10.1109\/34.799904","volume":"21","author":"HK Lee","year":"1999","unstructured":"Lee, H. K., & Kim, J. H. (1999). An HMM-based threshold model approach for gesture recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 21(10), 961\u2013973.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"9535_CR31","unstructured":"Lichman, M. (2013). UCI machine learning repository. University of California, Irvine, School of Information and Computer Sciences. http:\/\/archive.ics.uci.edu\/ml ."},{"key":"9535_CR32","unstructured":"Luo, X. (2011). Chinese speech recognition based on a hybrid SVM and HMM architecture. In International symposium on neural networks (pp.\u00a0629\u2013635). Berlin: Springer."},{"key":"9535_CR33","unstructured":"Ma, C., Randolph, M. A., & Drish, J. (2001). A support vector machines-based rejection technique for speech recognition. In IEEE international conference on acoustics, speech, and signal processing. proceedings (ICASSP\u201901) (Vol.\u00a01, pp.\u00a0381\u2013384). Salt Lake City: IEEE."},{"issue":"1","key":"9535_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10772-010-9082-0","volume":"14","author":"S Masmoudi","year":"2011","unstructured":"Masmoudi, S., Frikha, M., Chtourou, M., & Hamida, A. B. (2011). Efficient MLP constructive training algorithm using a neuron recruiting approach for isolated word recognition system. International Journal of Speech Technology, 14(1), 1\u201310.","journal-title":"International Journal of Speech Technology"},{"issue":"2","key":"9535_CR35","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1006\/csla.1996.0007","volume":"10","author":"T Matsui","year":"1996","unstructured":"Matsui, T., Kanno, T., & Furui, S. (1996). Speaker recognition using HMM composition in noisy environments. Computer Speech & Language, 10(2), 107\u2013116.","journal-title":"Computer Speech & Language"},{"issue":"3","key":"9535_CR36","first-page":"138","volume":"2","author":"L Muda","year":"2010","unstructured":"Muda, L., Begam, M., & Elamvazuthi, I. (2010). Voice recognition algorithms using mel frequency cepstral coefficient (MFCC) and dynamic time warping (DTW) techniques. Journal of Computing, 2(3), 138\u2013143.","journal-title":"Journal of Computing"},{"issue":"2","key":"9535_CR37","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"LR Rabiner","year":"1989","unstructured":"Rabiner, L. R. (1989). A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2), 257\u2013286.","journal-title":"Proceedings of the IEEE"},{"issue":"1","key":"9535_CR38","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/MASSP.1986.1165342","volume":"3","author":"LR Rabiner","year":"1986","unstructured":"Rabiner, L. R., & Juang, B. (1986). An introduction to hidden Markov models. IEEE ASSP magazine, 3(1), 4\u201316.","journal-title":"IEEE ASSP magazine"},{"key":"9535_CR39","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-642-76626-8_1","volume-title":"Speech recognition and understanding","author":"LR Rabiner","year":"1992","unstructured":"Rabiner, L. R., & Juang, B. H. (1992). Hidden Markov models for speech recognition\u2014strengths and limitations. In P. Laface & R. De Mori (Eds.), Speech recognition and understanding (pp.\u00a03\u201329). Berlin: Springer."},{"key":"9535_CR40","unstructured":"Ram\u013arez, M., Sotaquir\u00e1, M., De La Cruz, A., Maria, E., Avellaneda, G., & Ochoa, A. (2016). An automatic speech recognition system for helping visually impaired children to learn Braille. In XXI symposium on signal processing, images and artificial vision (STSIVA) (pp.\u00a01\u20134). Bucaramanga: IEEE."},{"key":"9535_CR41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-17163-0","volume-title":"Language identification using spectral and prosodic features","author":"KS Rao","year":"2015","unstructured":"Rao, K. S., Reddy, V. R., & Maity, S. (2015). Language identification using spectral and prosodic features. Berlin: Springer."},{"key":"9535_CR42","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1007\/978-3-642-12159-3_14","volume-title":"IAPR workshop on artificial neural networks in pattern recognition","author":"M Schmidt","year":"2010","unstructured":"Schmidt, M., Schels, M., & Schwenker, F. (2010). A hidden markov model based approach for facial expression recognition in image sequences. In F. Schwenker, N. El Gayar (Eds.), IAPR workshop on artificial neural networks in pattern recognition (pp.\u00a0149\u2013160). Berlin: Springer."},{"key":"9535_CR43","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1007\/978-3-642-31368-4_23","volume-title":"Autonomous and Intelligent Systems","author":"J Sun","year":"2012","unstructured":"Sun, J., Sun, J., Abida, K., & Karray, F. (2012). A novel template matching approach to speaker-independent arabic spoken digit recognition. In M. Kamel, F. Karray, & H. Hagras (Eds.), Autonomous and Intelligent Systems (pp.\u00a0192\u2013199). Berlin: Springer."},{"issue":"06","key":"9535_CR44","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1142\/S0218488501001253","volume":"9","author":"N Thubthong","year":"2001","unstructured":"Thubthong, N., & Kijsirikul, B. (2001). Support vector machines for Thai phoneme recognition. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 9(06), 803\u2013813.","journal-title":"International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems"},{"key":"9535_CR45","unstructured":"Wang, Q., & Ju, S. (2008). A mixed classifier based on combination of HMM and KNN. In Fourth international conference on natural computation, ICNC\u201908 (Vol.\u00a04, pp.\u00a038\u201342). Washington, DC: IEEE."},{"issue":"21","key":"9535_CR46","doi-asserted-by":"publisher","first-page":"3132","DOI":"10.1016\/j.ijleo.2015.07.073","volume":"126","author":"XH Wang","year":"2015","unstructured":"Wang, X. H., Liu, A., & Zhang, S. Q. (2015). New facial expression recognition based on FSVM and KNN. Optik-International Journal for Light and Electron Optics, 126(21), 3132\u20133134.","journal-title":"Optik-International Journal for Light and Electron Optics"},{"key":"9535_CR47","doi-asserted-by":"crossref","unstructured":"Xu, C. (2014). Model constrution in Speech recognition on time and space sampling point of view. In IEEE 9th Conference on industrial electronics and applications (ICIEA) (pp.\u00a01095\u20131097). IEEE.","DOI":"10.1109\/ICIEA.2014.6931328"},{"key":"9535_CR48","doi-asserted-by":"crossref","unstructured":"Xu, Y., Siohan, O., Simcha, D., Kumar, S., & Liao, H. (2015). Exemplar-based large vocabulary speech recognition using k-nearest neighbors. In International conference on acoustics, speech and signal processing (ICASSP), (pp.\u00a05167\u20135171). IEEE.","DOI":"10.1109\/ICASSP.2015.7178956"},{"issue":"3","key":"9535_CR49","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1007\/s10772-013-9221-5","volume":"17","author":"E Zarrouk","year":"2014","unstructured":"Zarrouk, E., Ayed, Y. B., & Gargouri, F. (2014). Hybrid continuous speech recognition systems by HMM, MLP and SVM: A comparative study. International Journal of Speech Technology, 17(3), 223\u2013233.","journal-title":"International Journal of Speech Technology"},{"issue":"7","key":"9535_CR50","doi-asserted-by":"publisher","first-page":"1421","DOI":"10.1109\/TASLP.2017.2694708","volume":"25","author":"H Zeinali","year":"2017","unstructured":"Zeinali, H., Sameti, H., & Burget, L. (2017). HMM-based phrase-independent i-vector extractor for text-dependent speaker verification. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 25(7), 1421\u20131435.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"9535_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, X., Povey, D., & Khudanpur, S. (2015). A diversity-penalizing ensemble training method for deep learning. In INTERSPEECH (pp.\u00a03590\u20133594).","DOI":"10.21437\/Interspeech.2015-712"},{"issue":"2","key":"9535_CR52","doi-asserted-by":"publisher","first-page":"e85458","DOI":"10.1371\/journal.pone.0085458","volume":"9","author":"X Zhang","year":"2014","unstructured":"Zhang, X., Sun, J., & Luo, Z. (2014). One-against-all weighted dynamic time warping for language-independent and speaker-dependent speech recognition in adverse conditions. PLoS ONE, 9(2), e85458. https:\/\/doi.org\/10.1371\/journal.pone.0085458 .","journal-title":"PLoS ONE"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-018-9535-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-018-9535-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-018-9535-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T20:38:44Z","timestamp":1751747924000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-018-9535-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7,16]]},"references-count":51,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2018,9]]}},"alternative-id":["9535"],"URL":"https:\/\/doi.org\/10.1007\/s10772-018-9535-4","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,7,16]]},"assertion":[{"value":"26 October 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 July 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 July 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}