{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T21:39:21Z","timestamp":1761514761723,"version":"3.37.3"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T00:00:00Z","timestamp":1619481600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T00:00:00Z","timestamp":1619481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2021,9]]},"DOI":"10.1007\/s10772-021-09847-7","type":"journal-article","created":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T18:04:28Z","timestamp":1619546668000},"page":"761-770","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["A comparative study for Arabic speech recognition system in noisy environments"],"prefix":"10.1007","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1540-2673","authenticated-orcid":false,"given":"Abdelkbir","family":"Ouisaadane","sequence":"first","affiliation":[]},{"given":"Said","family":"Safi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,4,27]]},"reference":[{"issue":"10","key":"9847_CR1","doi-asserted-by":"publisher","first-page":"1533","DOI":"10.1109\/TASLP.2014.2339736","volume":"22","author":"O Abdel-Hamid","year":"2014","unstructured":"Abdel-Hamid, O., Mohamed, A., Jiang, H., Deng, L., Penn, G., & Yu, D. (2014). Convolutional neural networks for speech recognition. IEEE Transactions on Audio, Speech and Language Processing, 22(10), 1533\u20131545.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"9847_CR2","doi-asserted-by":"crossref","unstructured":"Abdou, S.M., & Moussa, A.M. (2017). Arabic Speech Recognition: Challenges and State of the Art. In: Computational linguistics, speech and image processing for arabic language, vol. 4, (pp. 1\u201327), World Scientific.","DOI":"10.1142\/9789813229396_0001"},{"key":"9847_CR3","doi-asserted-by":"crossref","unstructured":"Abushariah, A.A.M., Gunawan, T.S., Khalifa, O.O., & Abushariah, M.A.M. (2010). English digits speech recognition system based on Hidden Markov Models. In: International conference on computer and communication engineering (ICCCE\u201910), (pp. 1\u20135).","DOI":"10.1109\/ICCCE.2010.5556819"},{"key":"9847_CR4","doi-asserted-by":"crossref","unstructured":"Alalshekmubara, A.K., & Smith, L.S. (2014). On improving the classification capability of reservoir computing for Arabic speech recognition. In: Artificial neural networks and machine learning \u2013 ICANN 2014, (pp. 225\u2013232).","DOI":"10.1007\/978-3-319-11179-7_29"},{"key":"9847_CR5","doi-asserted-by":"crossref","unstructured":"Alalshekmubarak, A., & Smith, L.S. (2014). On improving the classification capability of reservoir computing for Arabic speech recognition. In: Artificial neural networks and machine learning \u2013 ICANN 2014, Cham, (pp. 225\u2013232).","DOI":"10.1007\/978-3-319-11179-7_29"},{"key":"9847_CR6","unstructured":"Alotaibi, Y.A. (2004). Spoken Arabic digits recognizer using recurrent neural networks. In: Proceedings of the fourth IEEE international symposium on signal processing and information technology, (pp. 195\u2013199)."},{"issue":"4","key":"9847_CR7","doi-asserted-by":"publisher","first-page":"975","DOI":"10.1007\/s10579-020-09505-5","volume":"54","author":"E Alsharhan","year":"2020","unstructured":"Alsharhan, E., & Ramsay, A. (2020). Investigating the effects of gender, dialect, and training size on the performance of Arabic speech recognition. Language Resources and Evaluation, 54(4), 975\u2013998. https:\/\/doi.org\/10.1007\/s10579-020-09505-5.","journal-title":"Language Resources and Evaluation"},{"key":"9847_CR8","doi-asserted-by":"crossref","unstructured":"Aymen, M., Abdelaziz, A., Halim, S., & Maaref, H. (2011). hidden Markov models for automatic speech recognition. In: 2011 International conference on communications, computing and control applications (CCCA), (pp. 1\u20136).","DOI":"10.1109\/CCCA.2011.6031408"},{"key":"9847_CR9","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1016\/j.csl.2016.10.005","volume":"46","author":"J Barker","year":"2017","unstructured":"Barker, J., Marxer, R., Vincent, E., & Watanabe, S. (2017). The third \u201cCHiME\u201d speech separation and recognition challenge: Analysis and outcomes. Computer Speech & Language, 46, 605\u2013626.","journal-title":"Computer Speech & Language"},{"key":"9847_CR10","doi-asserted-by":"crossref","unstructured":"Chien, J.-T., & Misbullah, A. (2016). Deep long short-term memory networks for speech recognition. In: 2016 10th international symposium on Chinese spoken language processing (ISCSLP), (pp. 1\u20135).","DOI":"10.1109\/ISCSLP.2016.7918375"},{"key":"9847_CR11","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-1906-8","volume-title":"Novel techniques for dialectal Arabic speech recognition","author":"M Elmahdy","year":"2012","unstructured":"Elmahdy, M., Gruhn, R., & Minker, W. (2012). Novel techniques for dialectal Arabic speech recognition. New York: Springer."},{"key":"9847_CR12","unstructured":"El-Ramly, S.H., Abdel-Kader, N.S., & El-Adawi, R. (2002). Neural networks used for speech recognition. In: Proceedings of the nineteenth national radio science conference, (pp. 200\u2013207)."},{"key":"9847_CR13","doi-asserted-by":"crossref","unstructured":"Eltiraifi, O., Elbasheer, E., & Nawari, M. (2018). A comparative study of MFCC and LPCC features for speech activity detection using deep belief network. In: 2018 international conference on computer, control, electrical, and electronics engineering (ICCCEEE), (pp. 1\u20135).","DOI":"10.1109\/ICCCEEE.2018.8515821"},{"key":"9847_CR14","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A., & Hinton, G. (2013). Speech recognition with deep recurrent neural networks. In: 2013 IEEE international conference on acoustics, speech and signal processing, (pp. 6645\u20136649).","DOI":"10.1109\/ICASSP.2013.6638947"},{"issue":"2","key":"9847_CR15","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1049\/iet-spr.2018.5131","volume":"13","author":"A Guerid","year":"2019","unstructured":"Guerid, A., & Houacine, A. (2019). Recognition of isolated digits using DNN\u2013HMM and harmonic noise model. IET Signal Processing, 13(2), 207\u2013214.","journal-title":"IET Signal Processing"},{"key":"9847_CR16","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1007\/978-1-4471-0845-0_14","volume-title":"Speech processing, recognition and artificial neural networks","author":"J-P Haton","year":"1999","unstructured":"Haton, J.-P. (1999). Neural networks for automatic speech recognition: A review. In G. Chollet, M.-G. Di Benedetto, A. Esposito, & M. Marinaro (Eds.), Speech processing, recognition and artificial neural networks (pp. 259\u2013280). London: Springer."},{"issue":"6","key":"9847_CR17","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., et al. (2012). Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Processing Magazine, 29(6), 82\u201397.","journal-title":"IEEE Signal Processing Magazine"},{"key":"9847_CR18","doi-asserted-by":"crossref","unstructured":"Huggins-Daines, D., Kumar, M., Chan, A., Black, A.W., Ravishankar, M., & Rudnicky, A.I. (2006). Pocketsphinx: A free, real-time continuous speech recognition system for hand-held devices. In 2006 IEEE international conference on acoustics speech and signal processing proceedings, vol. 1, (pp. I\u2013I).","DOI":"10.1109\/ICASSP.2006.1659988"},{"issue":"3","key":"9847_CR19","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1080\/00401706.1991.10484833","volume":"33","author":"BH Juang","year":"1991","unstructured":"Juang, B. H., & Rabiner, L. R. (1991). Hidden Markov models for speech recognition. Technometrics, 33(3), 251\u2013272.","journal-title":"Technometrics"},{"issue":"1","key":"9847_CR20","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/s10772-018-09577-3","volume":"22","author":"V Kadyan","year":"2019","unstructured":"Kadyan, V., Mantri, A., Aggarwal, R. K., & Singh, A. (2019). A comparative study of deep neural network based Punjabi-ASR system. International Journal of Speech Technology, 22(1), 111\u2013119.","journal-title":"International Journal of Speech Technology"},{"issue":"4","key":"9847_CR21","doi-asserted-by":"publisher","first-page":"937","DOI":"10.1007\/s10772-017-9456-7","volume":"20","author":"MOM Khelifa","year":"2017","unstructured":"Khelifa, M. O. M., 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"},{"key":"9847_CR22","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1016\/j.heares.2016.10.004","volume":"349","author":"CG Le Prell","year":"2017","unstructured":"Le Prell, C. G., & Clavier, O. H. (2017). Effects of noise on speech recognition: Challenges for communication by service members. Hearing Research, 349, 76\u201389.","journal-title":"Hearing Research"},{"key":"9847_CR23","doi-asserted-by":"crossref","unstructured":"Manchanda, S., & Gupta, D. (2018). Hybrid approach of feature extraction and vector quantization in speech recognition. In: Proceedings of the second international conference on computational intelligence and informatics, (pp. 639\u2013645). Singapore.","DOI":"10.1007\/978-981-10-8228-3_59"},{"key":"9847_CR24","doi-asserted-by":"crossref","unstructured":"Novoa, J., Wuth, J., Escudero, J.P., Fredes, J., Mahu, R., & Yoma, N.B. DNN-HMM based Automatic Speech Recognition for HRI Scenarios. In Proceedings of the 2018 ACM\/IEEE international conference on human\u2013robot interaction, Chicago, USA, (pp. 150\u2013159).","DOI":"10.1145\/3171221.3171280"},{"key":"9847_CR25","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1016\/j.future.2020.05.034","volume":"112","author":"O Oueslati","year":"2020","unstructured":"Oueslati, O., Cambria, E., HajHmida, M. B., & Ounelli, H. (2020). A review of sentiment analysis research in Arabic language. Future Generation Computer Systems, 112, 408\u2013430. https:\/\/doi.org\/10.1016\/j.future.2020.05.034.","journal-title":"Future Generation Computer Systems"},{"key":"9847_CR26","unstructured":"Pearce, D., Hirsch, H., & Gmbh, E.E.D. (2000). The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions. In: ISCA ITRW ASR2000, (pp. 29\u201332)."},{"key":"9847_CR27","unstructured":"Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., & Vesely, K. (2011). The Kaldi speech recognition toolkit. In IEEE 2011 workshop on automatic speech recognition and understanding (No. CONF). IEEE Signal Processing Society."},{"issue":"2","key":"9847_CR28","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"},{"key":"9847_CR29","doi-asserted-by":"crossref","unstructured":"Roberts, W.J.J., & Willmore, J.P. (1999). Automatic speaker recognition using Gaussian mixture models. In: Proceedings 1999 information, decision and control. Data and information fusion symposium, signal processing and communications symposium and decision and control symposium. (Cat. No.99EX251), (pp. 465\u2013470).","DOI":"10.1109\/IDC.1999.754201"},{"key":"9847_CR30","doi-asserted-by":"crossref","unstructured":"Senior, A., Heigold, G., Bacchiani, M., & Liao, H. (2014). GMM-free DNN acoustic model training. In 2014 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 5602\u20135606.","DOI":"10.1109\/ICASSP.2014.6854675"},{"key":"9847_CR31","doi-asserted-by":"crossref","unstructured":"Senior, A., Heigold, G., Bacchiani, M., & Liao, H. (2014). GMM-free DNN acoustic model training. In: 2014 IEEE international conference on acoustics, speech and signal processing (ICASSP), (pp. 5602\u20135606).","DOI":"10.1109\/ICASSP.2014.6854675"},{"key":"9847_CR32","unstructured":"Shahin, M., Ahmed, B., McKechnie, J., Ballard, K., & Gutierrez-Osuna, R. (2014). Comparison of GMM-HMM and DNN-HMM based pronunciation verification techniques for use in the assessment of childhood apraxia of speech. In: 15th Annual conference of the international speech communication association (INTERSPEECH 2014): celebrating the diversity of spoken languages, (pp. 1583\u20131587)."},{"issue":"3","key":"9847_CR33","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","volume":"12","author":"A Varga","year":"1993","unstructured":"Varga, A., & Steeneken, H. J. M. (1993). Assessment for automatic speech recognition: II. NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systems. Speech Communication, 12(3), 247\u2013251.","journal-title":"Speech Communication"},{"key":"9847_CR34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71928-3_19","author":"VVR Vegesna","year":"2017","unstructured":"Vegesna, V. V. R., Gurugubelli, K., Vydana, H. K., Pulugandla, B., Shrivastava, M., & Vuppala, A. K. (2017). DNN-HMM acoustic modeling for large vocabulary telugu speech recognition. Mining Intelligence and Knowledge Exploration. https:\/\/doi.org\/10.1007\/978-3-319-71928-3_19.","journal-title":"Mining Intelligence and Knowledge Exploration"},{"key":"9847_CR35","doi-asserted-by":"crossref","unstructured":"Wahyuni, E.S. (2017). Arabic speech recognition using MFCC feature extraction and ANN classification. In 2017 2nd International conferences on information technology, information systems and electrical engineering, (pp. 22\u201325).","DOI":"10.1109\/ICITISEE.2017.8285499"},{"key":"9847_CR36","doi-asserted-by":"crossref","unstructured":"Yoshioka, T., Karita, S., & Nakatani, T. (2015). Far-field speech recognition using CNN-DNN-HMM with convolution in time. In: 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP), (pp. 4360\u20134364).","DOI":"10.1109\/ICASSP.2015.7178794"},{"key":"9847_CR37","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4471-5779-3","volume-title":"Automatic speech recognition: A deep learning approach","author":"D Yu","year":"2015","unstructured":"Yu, D., & Deng, L. (2015). Automatic speech recognition: A deep learning approach. London: Springer."},{"key":"9847_CR38","volume-title":"Intelligent robotics and applications","author":"W Zhang","year":"2019","unstructured":"Zhang, W., Zhai, M., Huang, Z., Liu, C., Li, W., & Cao, Y. (2019). Towards end-to-end speech recognition with deep multipath convolutional neural networks. In W. Zhang, M. Zhai, Z. Huang, C. Liu, W. Li, & Y. Cao (Eds.), Intelligent robotics and applications. Cham: Springer."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09847-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-021-09847-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09847-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,2]],"date-time":"2023-11-02T21:14:46Z","timestamp":1698959686000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-021-09847-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,27]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2021,9]]}},"alternative-id":["9847"],"URL":"https:\/\/doi.org\/10.1007\/s10772-021-09847-7","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2021,4,27]]},"assertion":[{"value":"29 June 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 April 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 April 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}