{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T08:12:03Z","timestamp":1761293523189},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2017,2,3]],"date-time":"2017-02-03T00:00:00Z","timestamp":1486080000000},"content-version":"unspecified","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":[[2017,6]]},"DOI":"10.1007\/s10772-017-9400-x","type":"journal-article","created":{"date-parts":[[2017,2,3]],"date-time":"2017-02-03T16:12:13Z","timestamp":1486138333000},"page":"205-224","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["An experimental framework for Arabic digits speech recognition in noisy environments"],"prefix":"10.1007","volume":"20","author":[{"given":"Azzedine","family":"Touazi","sequence":"first","affiliation":[]},{"given":"Mohamed","family":"Debyeche","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,2,3]]},"reference":[{"issue":"4","key":"9400_CR1","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1007\/s10579-011-9166-8","volume":"46","author":"MA Abushariah","year":"2012","unstructured":"Abushariah, M. A., Ainon, R. N., Zainuddin, R., Elshafei, M., & Khalifa, O. O. (2012). Phonetically rich and balanced text and speech corpora for Arabic language. Language Resources and Evaluation, 46(4), 601\u2013634.","journal-title":"Language Resources and Evaluation"},{"key":"9400_CR2","doi-asserted-by":"crossref","unstructured":"Alotaibi, Y. A. (2003). High performance Arabic digits recognizer using neural networks. In Proceedings of the international joint conference on neural networks, IJCNN, (pp.\u00a0670\u2013674).","DOI":"10.1109\/IJCNN.2003.1223444"},{"issue":"1","key":"9400_CR3","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.ins.2004.07.008","volume":"173","author":"YA Alotaibi","year":"2005","unstructured":"Alotaibi, Y. A. (2005). Investigating spoken Arabic digits in speech recognition setting. Information Sciences, 173(1), 115\u2013139.","journal-title":"Information Sciences"},{"issue":"1","key":"9400_CR4","doi-asserted-by":"crossref","first-page":"43","DOI":"10.4197\/Eng.19-1.3","volume":"19","author":"YA Alotaibi","year":"2008","unstructured":"Alotaibi, Y. A. (2008). Comparative study of ANN and HMM to Arabic digits recognition systems. Journal of King Abdulaziz Universitys, 19(1), 43\u201359.","journal-title":"Journal of King Abdulaziz Universitys"},{"key":"9400_CR5","unstructured":"Al-Zabibi, M. (1990). An acoustic-phonetic approach in automatic Arabic speech recognition (Doctoral dissertation, The British Library in Association with UMI,1990)."},{"issue":"1","key":"9400_CR6","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.engappai.2009.09.006","volume":"23","author":"A Amrouche","year":"2010","unstructured":"Amrouche, A., Debyeche, M., Taleb-Ahmed, A., Rouvaen, J. M., & Yagoub, M. C. E. (2010). An efficient speech recognition system in adverse conditions using the nonparametric regression. Engineering Applications of Artificial Intelligence, 23(1), 85\u201394.","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"9400_CR7","doi-asserted-by":"crossref","unstructured":"Applebaum, T. H., & Hanson, B. (1991). Regression features for recognition of speech in quiet and in noise. In Proceedings of the international conference on acoustics, speech, and signal processing, ICASSP, (pp.\u00a0985\u2013988).","DOI":"10.1109\/ICASSP.1991.150506"},{"key":"9400_CR8","unstructured":"AURORA project. (2006). AURORA speech recognition experimental framework. Retrieved September 15, 2016, from \nhttp:\/\/AURORA.hsnr.de\/index.html"},{"issue":"S1","key":"9400_CR9","doi-asserted-by":"crossref","first-page":"S97","DOI":"10.1121\/1.2003011","volume":"59","author":"R Bakis","year":"1976","unstructured":"Bakis, R. (1976). Continuous speech recognition via centisecond acoustic states. The Journal of the Acoustical Society of America, 59(S1), S97.","journal-title":"The Journal of the Acoustical Society of America"},{"key":"9400_CR10","unstructured":"Boersma, P., & Weenink, D. (2015). Praat: Doing phonetics by computer. Version 5.4.08. Retrieved September 15, 2016, from \nhttp:\/\/www.praat.org\/"},{"issue":"4","key":"9400_CR11","first-page":"1366","volume":"15","author":"X Cui","year":"2007","unstructured":"Cui, X., & Gong, Y. (2007). A study of variable-parameter Gaussian mixture hidden Markov modeling for noisy speech recognition. IEEE Transactions on Acoustics, Speech, and Signal Processing, 15(4), 1366\u20131376.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"9400_CR12","unstructured":"ELRA. (2005). NEMLAR broadcast news speech corpus. ELRA catalogue, ELRA-S0219. Retrieved September 15, 2016, from \nhttp:\/\/catalog.elra.info\/product_info.php?products id = 874"},{"key":"9400_CR13","unstructured":"ETSI document ES 201 108. (2003a). Speech processing, transmission, and quality aspects (stq): Distributed speech recognition; front-end feature extraction algorithm; compression algorithms. Version 1.1.3."},{"key":"9400_CR14","unstructured":"ETSI document ES 202 211. (2003b). Speech processing, transmission, and quality aspects (STQ): Distributed speech recognition; extended front-end feature extraction algorithm; compression algorithms; back-end speech reconstruction algorithm. Version 1.1.1."},{"key":"9400_CR15","unstructured":"ETSI document ES 202 050. (2007). Speech processing, transmission, and quality aspects (STQ): Distributed speech recognition; advanced front-end feature extraction algorithm; compression algorithms. Version 1.1.5."},{"issue":"11","key":"9400_CR16","doi-asserted-by":"crossref","first-page":"2783","DOI":"10.1093\/ietisy\/e89-d.11.2783","volume":"89","author":"M Fujimoto","year":"2006","unstructured":"Fujimoto, M., Takeda, K., & Nakamura, S. (2006). CENSREC-3: An evaluation framework for Japanese speech recognition in real car-driving environments. IEICE Transactions on Information and Systems, 89(11), 2783\u20132793.","journal-title":"IEICE Transactions on Information and Systems"},{"issue":"2","key":"9400_CR17","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1109\/TASSP.1981.1163530","volume":"29","author":"S Furui","year":"1981","unstructured":"Furui, S. (1981). Cepstral analysis technique for automatic speaker verification. Acoustics, IEEE Transactions on Acoustics, Speech, and Signal Processing, 29(2), 254\u2013272.","journal-title":"Acoustics, IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"issue":"1","key":"9400_CR18","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1109\/TASSP.1986.1164788","volume":"34","author":"S Furui","year":"1986","unstructured":"Furui, S. (1986). Speaker-independent isolated word recognition using dynamic features of speech spectrum. IEEE Transactions on Acoustics, Speech, and Signal Processing, 34(1), 52\u201359.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"issue":"4","key":"9400_CR19","doi-asserted-by":"crossref","first-page":"358","DOI":"10.1109\/89.917681","volume":"9","author":"A Ganapathiraju","year":"2001","unstructured":"Ganapathiraju, A., Hamaker, J., Picone, J., Ordowski, M., & Doddington, G. R. (2001). Syllable-based large vocabulary continuous speech recognition. IEEE Transactions on Acoustics, Speech, and Signal Processing, 9(4), 358\u2013366.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"9400_CR20","doi-asserted-by":"crossref","unstructured":"Gish, H., & Ng, K. (1996). Parametric trajectory models for speech recognition. In Proceedings of the international conference on spoken language processing, ICSLP, (pp.\u00a0466\u2013469).","DOI":"10.1109\/ICSLP.1996.607155"},{"key":"9400_CR21","doi-asserted-by":"crossref","unstructured":"Hajj, N., & Awad, M. (2013). Weighted entropy cortical algorithms for isolated Arabic speech recognition. In Proceedings of the International Joint Conference on Neural Networks, IJCNN, (pp.\u00a01\u20137).","DOI":"10.1109\/IJCNN.2013.6706753"},{"key":"9400_CR22","unstructured":"Hirsch, H.-G., & Pearce, D. (2000). The AURORA experimental framework for the performance evaluation of speech recognition systems under noisy conditions. In Proceedings of ISCA tutorial and research workshop, (pp.\u00a0181\u2013188)."},{"key":"9400_CR23","unstructured":"Hirsch, H-G. (2005). FaNT, filtering and noise adding tool. Retrieved September 15, 2016, from \nhttp:\/\/dnt.kr.hsnr.de\/"},{"key":"9400_CR24","unstructured":"Hirsch, H-G., & Pearce, D. (2006). Applying the advanced ETSI frontend to the AURORA-2 task. technical report, Version 1.1."},{"issue":"2","key":"9400_CR25","doi-asserted-by":"crossref","first-page":"1306","DOI":"10.1121\/1.2939132","volume":"124","author":"G Hu","year":"2008","unstructured":"Hu, G., & Wang, D. (2008). Segregation of unvoiced speech from nonspeech interference. The Journal of the Acoustical Society of America, 124(2), 1306\u20131319.","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"3","key":"9400_CR26","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1007\/s10772-008-9009-1","volume":"9","author":"H Hyassat","year":"2006","unstructured":"Hyassat, H., & Abu Zitar, R. (2006). Arabic speech recognition using SPHINX engine. International Journal of Speech Technology, 9(3), 133\u2013150.","journal-title":"International Journal of Speech Technology"},{"key":"9400_CR27","unstructured":"ITU-T, Recommendation P.830. (1992). Subjective performance assessment of telephone-band and wideband digital codecs. Geneva, Switzerland."},{"key":"9400_CR28","unstructured":"ITU-T, Recommendation G.712. (1996). Transmission performance characteristics for pulse code modulation channels, Geneva, Switzerland."},{"key":"9400_CR29","unstructured":"Knoblich, U. (2000). Description and baseline results for the subset of the Speechdat-Car Italian database used for ETSI STQ Aurora WI008 advanced DSR front-end evaluation. Alcatel. AU\/237\/00."},{"key":"9400_CR30","doi-asserted-by":"crossref","unstructured":"Lee, C. H., Rabiner, L., Pieraccini, R., & Wilpon, J. (1990). Acoustic modeling of subword units for speech recognition. In Proceedings of the international conference on acoustics, speech, and signal processing, ICASSP, (pp.\u00a0721\u2013724).","DOI":"10.1109\/ICASSP.1990.115885"},{"key":"9400_CR31","volume-title":"Automatic speech and speaker recognition: advanced topics","author":"CH Lee","year":"1996","unstructured":"Lee, C. H., Soong, F. K., & Paliwal, K. K. (1996). Automatic speech and speaker recognition: advanced topics (Vol.\u00a0355). London: Springer Science & Business Media."},{"key":"9400_CR32","doi-asserted-by":"crossref","unstructured":"Leonard, R. (1984). A database for speaker-independent digit recognition. In Proceedings of the international conference on acoustics, speech, and signal processing, ICASSP, (pp.\u00a0328\u2013331).","DOI":"10.1109\/ICASSP.1984.1172716"},{"key":"9400_CR33","unstructured":"Lindberg, B. (2001). Danish Speechdat-Car Digits database for ETSI STQ AURORA advanced DSR. CPK, Aalborg University. AU\/378\/01."},{"key":"9400_CR34","unstructured":"Ma, D., & ZENG, X. (2012). An improved VQ based algorithm for recognizing speaker-independent isolated words. In Proceedings of the international conference on machine learning and cybernetics, ICMLC, (pp.\u00a0792\u2013796)."},{"key":"9400_CR35","volume-title":"Spanish SDC-AURORA database used for ETSI STQ AURORA WI008 advanced DSR front-end evaluation, description and baseline results","author":"D Macho","year":"2000","unstructured":"Macho, D. (2000). Spanish SDC-AURORA database used for ETSI STQ AURORA WI008 advanced DSR front-end evaluation, description and baseline results. Barcelona: Universitat Politecnica de Catalunya (UPC). AU\/271\/00."},{"issue":"3","key":"9400_CR36","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1093\/ietisy\/e88-d.3.535","volume":"88","author":"S Nakamura","year":"2005","unstructured":"Nakamura, S., Takeda, K., Yamamoto, K., Yamada, T., Kuroiwa, S., Kitaoka, N., Nishiura, T., Sasou, A., Mizumachi, M., Miyajima, C., Fujimoto, M., & Endo, T. (2005). AURORA-2J: An evaluation framework for Japanese noisy speech recognition. IEICE Transaction on Information and Systems, 88(3), 535\u2013544.","journal-title":"IEICE Transaction on Information and Systems"},{"issue":"4","key":"9400_CR37","doi-asserted-by":"crossref","first-page":"739","DOI":"10.1080\/14640748608401623","volume":"38","author":"M Naveh-Benjamin","year":"1986","unstructured":"Naveh-Benjamin, M., & Ayres, T. J. (1986). Digit span, reading rate, and linguistic relativity. The Quarterly Journal of Experimental Psychology, 38(4), 739\u2013751.","journal-title":"The Quarterly Journal of Experimental Psychology"},{"issue":"4","key":"9400_CR38","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1007\/BF02108643","volume":"2","author":"SFDC Neto","year":"1999","unstructured":"Neto, S.F.D.C. (1999). The ITU-T software tool library. International Journal of Speech Technology, 2(4), 259\u2013272.","journal-title":"International Journal of Speech Technology"},{"key":"9400_CR39","unstructured":"Netsch, L. (2001). Description and baseline results for the subset of the Speechdat-Car German database used for ETSI STQ AURORA WI008 advanced DSR front-end evaluation. Texas Instruments. AU\/273\/00."},{"key":"9400_CR40","unstructured":"Nishiura, T., Nakayama, M., Denda, Y., Kitaoka, N., Yamamoto, K., Yamada, T., et al. (2008). Evaluation framework for distant-talking speech recognition under reverberant: Newest part of the CENSREC Series. In Proceedings of the language resources and evaluation conference, LREC, (pp.\u00a01828\u20131834)."},{"key":"9400_CR41","unstructured":"Nokia. (2000). Baseline results for subset of Speechdat-Car Finnish database used for ETSI STQ WI008 advanced front-end evaluation. AU\/225\/00."},{"key":"9400_CR42","unstructured":"Pearce, D. (2000). Enabling new speech driven services for mobile devices: An overview of the ETSI standards activities for distributed speech recognition. In Proceedings of the voice input\/output applied society conference, AVIOS (pp. 83\u201386). San Jose: AVIOS"},{"key":"9400_CR43","doi-asserted-by":"crossref","unstructured":"Pearce, D. (2001). Developing the ETSI AURORA advanced distributed speech recognition front-end & what next?. In Proceedings of the workshop on automatic speech recognition and understanding, ASRU, (pp.\u00a0131\u2013134).","DOI":"10.1109\/ASRU.2001.1034605"},{"issue":"2","key":"9400_CR44","doi-asserted-by":"crossref","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":"9400_CR45","volume-title":"Fundamentals of speech recognition","author":"LR Rabiner","year":"1993","unstructured":"Rabiner, L. R., & Juang, B. H. (1993). Fundamentals of speech recognition (Vol.\u00a014). Englewood Cliffs: PTR Prentice Hall."},{"issue":"8","key":"9400_CR46","doi-asserted-by":"crossref","first-page":"1214","DOI":"10.1109\/29.31269","volume":"37","author":"LR Rabiner","year":"1989","unstructured":"Rabiner, L. R., Wilpon, J. G., & Soong, F. K. (1989). High performance connected digit recognition using hidden Markov models. IEEE Transactions on Acoustics, Speech, and Signal Processing, 37(8), 1214\u20131225.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"9400_CR47","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511486975","volume-title":"A reference grammar of modern standard Arabic","author":"KC Ryding","year":"2005","unstructured":"Ryding, K. C. (2005). A reference grammar of modern standard Arabic. Cambridge: Cambridge University Press."},{"key":"9400_CR48","unstructured":"Siemund, R., Heuft, B., Choukri, K., Emam, O., Maragoudakis, E., Tropf, H., et al. (2002). OrienTel: Arabic speech resources for the IT market. In Proceedings of the language resources and evaluation conference, LREC."},{"issue":"6","key":"9400_CR49","doi-asserted-by":"crossref","first-page":"871","DOI":"10.1109\/29.1598","volume":"36","author":"FK Soong","year":"1988","unstructured":"Soong, F. K., & Rosenberg, A. E. (1988). On the use of instantaneous and transitional spectral information in speaker recognition. IEEE Transactions on Acoustics, Speech, and Signal Processing, 36(6), 871\u2013879.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"9400_CR50","unstructured":"The Linguistic Data Consortium. (2014). King Saud University database. Retrieved September 15, 2016, from \nhttps:\/\/catalog.ldc.upenn.edu\/ldc2014s02"},{"key":"9400_CR51","unstructured":"World Bank (2016). Retrieved September 15, 2016, from \nhttp:\/\/data.worldbank.org\/region\/ARB"},{"key":"9400_CR52","volume-title":"The HTK Book. Version 3.4","author":"S Young","year":"2006","unstructured":"Young, S., Evermann, G., Gales, M., Hain, T., Kershaw, D., Liu, X., Moore, G., Odell, J., Ollason, D., Povey, D., Valtchev, V., & Woodland, P. (2006). The HTK Book. Version 3.4. Cambridge: Cambridge University, Engineering Department."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-017-9400-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-017-9400-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-017-9400-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,5,17]],"date-time":"2017-05-17T11:04:49Z","timestamp":1495019089000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-017-9400-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,2,3]]},"references-count":52,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2017,6]]}},"alternative-id":["9400"],"URL":"https:\/\/doi.org\/10.1007\/s10772-017-9400-x","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,2,3]]}}}