{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,3]],"date-time":"2026-01-03T15:07:57Z","timestamp":1767452877387,"version":"3.37.3"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T00:00:00Z","timestamp":1721606400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T00:00:00Z","timestamp":1721606400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1007\/s10772-024-10130-8","type":"journal-article","created":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T05:02:05Z","timestamp":1721624525000},"page":"673-686","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["ArabRecognizer: modern standard Arabic speech recognition inspired by DeepSpeech2 utilizing Franco-Arabic"],"prefix":"10.1007","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1771-4205","authenticated-orcid":false,"given":"Mohammed M.","family":"Nasef","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amr A.","family":"Elshall","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amr M.","family":"Sauber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,7,22]]},"reference":[{"key":"10130_CR1","unstructured":"Abdelhamid, A., Alsayadi, H. A., Hegazy, I., & Fayed, Z. T. (2020). End-to-end Arabic speech recognition: A review. Bibliotheca Alexandrina, Sep 2020. Retrieved Dec 12, 2023 from http:\/\/research.asu.edu.eg\/handle\/123456789\/178165"},{"key":"10130_CR2","doi-asserted-by":"publisher","DOI":"10.1590\/1983-3652.2024.46952","volume":"17","author":"WM Akasheh","year":"2024","unstructured":"Akasheh, W. M., Haider, A. S., Al-Saideen, B., & Sahari, Y. (2024). Artificial intelligence-generated Arabic subtitles: Insights from Veed.io\u2019s automatic speech recognition system of Jordanian Arabic. Texto Livre, 17, e46952. https:\/\/doi.org\/10.1590\/1983-3652.2024.46952","journal-title":"Texto Livre"},{"issue":"2","key":"10130_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.asej.2021.06.020","volume":"13","author":"FS Al-Anzi","year":"2022","unstructured":"Al-Anzi, F. S., & AbuZeina, D. (2022). Synopsis on Arabic speech recognition. Ain Shams Engineering Journal, 13(2), 101534. https:\/\/doi.org\/10.1016\/j.asej.2021.06.020","journal-title":"Ain Shams Engineering Journal"},{"key":"10130_CR4","doi-asserted-by":"publisher","unstructured":"AlHanai, T., Hsu, W.-N. & Glass, J. (2016). Development of the MIT ASR system for the 2016 Arabic multi-genre broadcast challenge. In 2016 IEEE spoken language technology workshop (SLT), (pp. 299\u2013304), San Diego, CA, December 2016. IEEE. https:\/\/doi.org\/10.1109\/SLT.2016.7846280","DOI":"10.1109\/SLT.2016.7846280"},{"issue":"4","key":"10130_CR5","doi-asserted-by":"publisher","first-page":"67","DOI":"10.4018\/jitr.2009062905","volume":"2","author":"M Ali","year":"2009","unstructured":"Ali, M., Elshafei, M., Al-Ghamdi, M., & Al-Muhtaseb, H. (2009). Arabic phonetic dictionaries for speech recognition.  Journal of Information Technology Research, 2(4), 67\u201380. https:\/\/doi.org\/10.4018\/jitr.2009062905","journal-title":"J. Inf. Technol. Res."},{"issue":"1","key":"10130_CR6","doi-asserted-by":"publisher","first-page":"43","DOI":"10.4197\/Eng.19-1.3","volume":"19","author":"Y Alotaibi","year":"2008","unstructured":"Alotaibi, Y. (2008). Comparative study of ANN and HMM to Arabic digits recognition systems. Journal of King Abdulaziz University-Engineering Science, 19(1), 43\u201360. https:\/\/doi.org\/10.4197\/Eng.19-1.3","journal-title":"Journal of King Abdulaziz University-Engineering Science"},{"key":"10130_CR7","unstructured":"Amodei, D., Ananthanarayanan, S., Anubhai, R., Bai, J., Battenberg, E., Case, C., Casper, J., Catanzaro, B., Cheng, Q., Chen, G., et al. (2016). Deep Speech 2\u202f: End-to-end speech recognition in English and Mandarin, ICML (2016) (pp. 173\u2013182). 1\/2022"},{"key":"10130_CR8","doi-asserted-by":"crossref","unstructured":"Cardinal, P., et al. (2014). Recent advances in ASR applied to an Arabic transcription system for Al-Jazeera. In Proceedings of annual conference in International Speech Communication Association (Interspeech), (pp. 2088\u20132092), January 2014.","DOI":"10.21437\/Interspeech.2014-474"},{"key":"10130_CR9","volume-title":"Deep learning with Python","author":"F Chollet","year":"2021","unstructured":"Chollet, F. (2021). Deep learning with Python. Manning: Second Edition."},{"key":"10130_CR10","unstructured":"Common voice dataset. https:\/\/commonvoice.mozilla.org\/en\/datasets 2\/2022"},{"key":"10130_CR11","doi-asserted-by":"publisher","unstructured":"Elmahdy, M., Gruhn, R., Minker, W., & Abdennadher, S. (2009). Modern standard Arabic based multilingual approach for dialectal Arabic speech recognition. In 2009 eighth international symposium on natural language processing (pp. 169\u2013174), Bangkok, Thailand, October 2009. IEEE. https:\/\/doi.org\/10.1109\/SNLP.2009.5340923","DOI":"10.1109\/SNLP.2009.5340923"},{"key":"10130_CR12","doi-asserted-by":"publisher","unstructured":"Essa, E. M., Tolba, A. S., & Elmougy, S. (2008) A comparison of combined classifier architectures for Arabic speech recognition. In 2008 international conference on computer engineering & systems, (pp. 149\u2013153), Cairo, Egypt,November 2008. IEEE. https:\/\/doi.org\/10.1109\/ICCES.2008.4772985","DOI":"10.1109\/ICCES.2008.4772985"},{"key":"10130_CR13","unstructured":"Forsberg, M. (2003). Why is speech recognition difficult? Chalmers University of Technology ResearchGate. March 2003 (pp. 1\u20139)."},{"issue":"1","key":"10130_CR14","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1186\/s13636-021-00217-4","volume":"2021","author":"A-L Georgescu","year":"2021","unstructured":"Georgescu, A.-L., Pappalardo, A., Cucu, H., & Blott, M. (2021). Performance vs hardware requirements in state-of-the-art automatic speech recognition. EURASIP Journal of Audio Speech Music Processing, 2021(1), 28. https:\/\/doi.org\/10.1186\/s13636-021-00217-4","journal-title":"EURASIP Journal of Audio Speech Music Processing"},{"issue":"1","key":"10130_CR15","doi-asserted-by":"publisher","first-page":"23","DOI":"10.3844\/ajassp.2007.23.32","volume":"4","author":"RA Haraty","year":"2007","unstructured":"Haraty, R. A., & El Ariss, O. (2007). CASRA+: A colloquial Arabic speech recognition application. American Journal of Applied Sciences, 4(1), 23\u201332. https:\/\/doi.org\/10.3844\/ajassp.2007.23.32","journal-title":"American Journal of Applied Sciences"},{"key":"10130_CR16","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1007\/978-1-4471-4739-8_20","volume-title":"Research and Development in Intelligent Systems XXIX","author":"N Hmad","year":"2012","unstructured":"Hmad, N., & Allen, T. (2012). Biologically inspired continuous Arabic speech recognition. In M. Bramer & M. Petridis (Eds.), Research and development in intelligent systems XXIX (pp. 245\u2013258). Springer."},{"key":"10130_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101272","volume":"71","author":"A Hussein","year":"2022","unstructured":"Hussein, A., Watanabe, S., & Ali, A. (2022). Arabic speech recognition by end-to-end, modular systems and human. Computer Speech & Language, 71, 101272. https:\/\/doi.org\/10.1016\/j.csl.2021.101272","journal-title":"Computer Speech & Language"},{"issue":"3\u20134","key":"10130_CR18","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/s10772-008-9009-1","volume":"9","author":"H Hyassat","year":"2006","unstructured":"Hyassat, H., & AbuZitar, R. (2006). Arabic speech recognition using SPHINX engine. International Journal of Speech Technology, 9(3\u20134), 133\u2013150. https:\/\/doi.org\/10.1007\/s10772-008-9009-1","journal-title":"International Journal of Speech Technology"},{"key":"10130_CR19","unstructured":"MGB2 dataset: https:\/\/arabicspeech.org\/mgb2\/"},{"key":"10130_CR20","unstructured":"MGB3 dataset: https:\/\/arabicspeech.org\/mgb3-asr-2\/"},{"key":"10130_CR21","unstructured":"MGB5 dataset: https:\/\/arabicspeech.org\/mgb5\/"},{"key":"10130_CR22","unstructured":"Mohamed, O., Shedeed, H., Tolba, M., & Gadalla, M. (2013). Morphame-based Arabic language modeling for automatic speech recognition, Jun 2013."},{"key":"10130_CR23","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2023.0140416","author":"A Moondra","year":"2023","unstructured":"Moondra, A., & Chahal, P. (2023). Improved speaker recognition for degraded human voice using modified-MFCC and LPC with CNN. IJACSA. https:\/\/doi.org\/10.14569\/IJACSA.2023.0140416","journal-title":"IJACSA"},{"issue":"8","key":"10130_CR24","doi-asserted-by":"publisher","first-page":"10617","DOI":"10.1007\/s13369-023-07670-7","volume":"48","author":"S Nasr","year":"2023","unstructured":"Nasr, S., Duwairi, R., & Quwaider, M. (2023). End-to-end speech recognition for Arabic dialects. Arabian Journal for Science and Engineering, 48(8), 10617\u201310633. https:\/\/doi.org\/10.1007\/s13369-023-07670-7","journal-title":"Arabian Journal for Science and Engineering"},{"issue":"10","key":"10130_CR25","doi-asserted-by":"publisher","first-page":"2965","DOI":"10.1016\/j.patcog.2008.05.008","volume":"41","author":"D O\u2019Shaughnessy","year":"2008","unstructured":"O\u2019Shaughnessy, D. (2008). Automatic speech recognition: History, methods and challenges. Pattern Recognition, 41(10), 2965\u20132979. https:\/\/doi.org\/10.1016\/j.patcog.2008.05.008","journal-title":"Pattern Recognition"},{"key":"10130_CR26","doi-asserted-by":"publisher","unstructured":"Obaidah, Q. A., et al. (2024). A new benchmark for evaluating automatic speech recognition in the Arabic call domain. arXiv, 2024. https:\/\/doi.org\/10.48550\/ARXIV.2403.04280","DOI":"10.48550\/ARXIV.2403.04280"},{"key":"10130_CR27","unstructured":"Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., Hannemann, M., Motlicek, P., Qian, Y., Schwarz, P., et al. (2011). The Kaldi speech recognition toolkit. In IEEE 2011 workshop on automatic speech recognition and understanding. IEEE Signal Processing Society, 2011, number EPFL-CONF-192584."},{"key":"10130_CR28","doi-asserted-by":"publisher","first-page":"39689","DOI":"10.1109\/ACCESS.2024.3376237","volume":"12","author":"A Rahman","year":"2024","unstructured":"Rahman, A., Kabir, Md. M., Mridha, M. F., Alatiyyah, M., Alhasson, H. F., & Alharbi, S. S. (2024). Arabic speech recognition: Advancement and challenges. IEEE Access, 12, 39689\u201339716. https:\/\/doi.org\/10.1109\/ACCESS.2024.3376237","journal-title":"IEEE Access"},{"key":"10130_CR29","doi-asserted-by":"publisher","unstructured":"Rana, R. (2016). Gated Recurrent Unit (GRU) for emotion classification from noisy speech. arXiv, 2016. https:\/\/doi.org\/10.48550\/ARXIV.1612.07778","DOI":"10.48550\/ARXIV.1612.07778"},{"key":"10130_CR30","unstructured":"Yu, D., Eversole, A., Seltzer, M., Yao, K., Huang, Z., Guenter, B., Kuchaiev, O., Zhang, Y., Seide, F., Wang, H., et al. (2014). An introduction to computational networks and the computational network toolkit, Technical report."},{"key":"10130_CR31","doi-asserted-by":"publisher","unstructured":"Zhang, S., Hu, Y., & Bian, G. (2017). Research on string similarity algorithm based on Levenshtein Distance. In 2017 IEEE 2nd advanced information technology, electronic and automation control conference (IAEAC), (pp. 2247\u20132251), Chongqing, China, March 2017. IEEE. https:\/\/doi.org\/10.1109\/IAEAC.2017.8054419","DOI":"10.1109\/IAEAC.2017.8054419"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-024-10130-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-024-10130-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-024-10130-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,12]],"date-time":"2024-09-12T12:11:08Z","timestamp":1726143068000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-024-10130-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,22]]},"references-count":31,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["10130"],"URL":"https:\/\/doi.org\/10.1007\/s10772-024-10130-8","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2024,7,22]]},"assertion":[{"value":"18 February 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 July 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"No experiments involving humans or animals in this article.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"All authors gave their consent.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}