{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T00:11:09Z","timestamp":1768522269952,"version":"3.49.0"},"publisher-location":"Cham","reference-count":65,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031853623","type":"print"},{"value":"9783031853630","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-85363-0_2","type":"book-chapter","created":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T08:50:54Z","timestamp":1741078254000},"page":"13-31","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Review of\u00a0Speech Recognition and\u00a0Application to\u00a0Arabic Speech Recognition"],"prefix":"10.1007","author":[{"given":"Eman","family":"Aboelela","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Omar","family":"Mansour","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,3,5]]},"reference":[{"key":"2_CR1","doi-asserted-by":"publisher","unstructured":"Rahman, A., Kabir, M.M., Mridha, M.M., Alatiyyah, M., Alhasson, H.F., Alharbi, S.S.: Arabic Speech recognition: advancement and challenges. IEEE Access 12, 39689\u201339716 (2024). https:\/\/doi.org\/10.1109\/ACCESS.2024.3376237","DOI":"10.1109\/ACCESS.2024.3376237"},{"key":"2_CR2","doi-asserted-by":"publisher","first-page":"8898","DOI":"10.3390\/app12178898","volume":"12","author":"A Dhouib","year":"2022","unstructured":"Dhouib, A., Othman, A., Elghoul, O., Khribi, M.K., Sinani, A.: Arabic automatic speech recognition: a systematic literature review. Appl. Sci. 12, 8898 (2022). https:\/\/doi.org\/10.3390\/app12178898","journal-title":"Appl. Sci."},{"key":"2_CR3","unstructured":"Emerging Technologies. http:\/\/www.em-t.com\/"},{"key":"2_CR4","unstructured":"ADCB. http:\/\/www.adcb.com\/"},{"key":"2_CR5","doi-asserted-by":"publisher","unstructured":"Mohammed, A., Sunar, M.S., Salam, M.S.H.: Quranic verses verification using speech recognition techniques. Jurnal TeknologiJurnal Teknologi 73 (2015). https:\/\/doi.org\/10.11113\/jt.v73.4200","DOI":"10.11113\/jt.v73.4200"},{"key":"2_CR6","doi-asserted-by":"publisher","unstructured":"Ibrahim, N.J., Idris, M.Y.I., Razak, Z., Rahman, N.N.A.: Automated tajweed checking rules engine for Quranic learning. Multicult. Educ. Technol. J. 7, 275\u2013287 (2013). https:\/\/doi.org\/10.1108\/metj-03-2013-0012","DOI":"10.1108\/metj-03-2013-0012"},{"key":"2_CR7","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1016\/j.eij.2016.04.002","volume":"17","author":"MYE Amrani","year":"2016","unstructured":"Amrani, M.Y.E., Rahman, M.H., Wahiddin, M.R., Shah, A.: Building CMU Sphinx language model for the Holy Quran using simplified Arabic phonemes. Egypt. Inform. J. 17, 305\u2013314 (2016). https:\/\/doi.org\/10.1016\/j.eij.2016.04.002","journal-title":"Egypt. Inform. J."},{"key":"2_CR8","unstructured":"Alotaibi, Y.A., Hussain, A.: Comparative analysis of Arabic vowels using formants and an automatic speech recognition system. Int. J. Signal Process. Image Process. Pattern Recognit. 3, 11\u201322 (2010). https:\/\/api.semanticscholar.org\/CorpusID:10418480"},{"key":"2_CR9","unstructured":"Young, S., Jansen, J., Odell, J., Ollason, D., Woodland, P.: The HTK book (1995). http:\/\/publications.eng.cam.ac.uk\/331214\/"},{"key":"2_CR10","unstructured":"EL-Mashed, S.Y., Sharway, M.I., Zayed, H.H.: Speaker independent Arabic speech recognition using support vector machine. In: Proceedings of ICI 11, Conference and Exhibition on Information and Communication Technology, vol. 11, pp. 401\u2013416 (2011). https:\/\/api.semanticscholar.org\/CorpusID:4664418"},{"key":"2_CR11","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1007\/s10772-021-09847-7","volume":"24","author":"A Ouisaadane","year":"2021","unstructured":"Ouisaadane, A., Safi, S.: A comparative study for Arabic speech recognition system in noisy environments. Int. J. Speech Technol. 24, 761\u2013770 (2021). https:\/\/doi.org\/10.1007\/s10772-021-09847-7","journal-title":"Int. J. Speech Technol."},{"key":"2_CR12","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1049\/sil2.12057","volume":"15","author":"HA Alsayadi","year":"2021","unstructured":"Alsayadi, H.A., Abdelhamid, A.A., Hegazy, I., Fayed, Z.T.: Arabic speech recognition using end-to-end deep learning. IET Signal Process. 15, 521\u2013534 (2021). https:\/\/doi.org\/10.1049\/sil2.12057","journal-title":"IET Signal Process."},{"key":"2_CR13","doi-asserted-by":"publisher","unstructured":"Watanabe, S., et al.: ESPnet: end-to-end speech processing toolkit. In: Proceedings of INTERSPEECH 2018, pp. 2207\u20132211 (2018). https:\/\/doi.org\/10.21437\/interspeech.2018-1456","DOI":"10.21437\/interspeech.2018-1456"},{"key":"2_CR14","doi-asserted-by":"publisher","unstructured":"Wang, Y., et al.: Espresso: a fast end-to-end neural speech recognition toolkit. In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 136\u2013143 (2019). https:\/\/doi.org\/10.1109\/asru46091.2019.9003968","DOI":"10.1109\/asru46091.2019.9003968"},{"key":"2_CR15","doi-asserted-by":"publisher","unstructured":"Elmahdy, M., Gruhn, R., Minker, W., Abdennadher, S.: Modern standard Arabic based multilingual approach for dialectal Arabic speech recognition. In: Proceedings of 2009 Eighth International Symposium on Natural Language Processing, pp. 169\u2013174 (2009). https:\/\/doi.org\/10.1109\/snlp.2009.5340923","DOI":"10.1109\/snlp.2009.5340923"},{"key":"2_CR16","doi-asserted-by":"publisher","unstructured":"Aldjanabi, W., Dahou, A., Al-Qaness, M.A.A., Elaziz, M.A., Helmi, A.M., Dama\u0161evi\u010dius, R.: Arabic offensive and hate speech detection using a cross-corpora multi-task learning model. Informatics 8 (2021). https:\/\/doi.org\/10.3390\/informatics8040069","DOI":"10.3390\/informatics8040069"},{"key":"2_CR17","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/s10772-008-9009-1","volume":"9","author":"H Hyassat","year":"2006","unstructured":"Hyassat, H., Zitar, R.A.: Arabic speech recognition using SPHINX engine. Int. J. Speech Technol. 9, 133\u2013150 (2006). https:\/\/doi.org\/10.1007\/s10772-008-9009-1","journal-title":"Int. J. Speech Technol."},{"key":"2_CR18","doi-asserted-by":"publisher","unstructured":"Wazir, A.S.M.B., Chuah, J.H.: Spoken Arabic digits recognition using deep learning. In: Proceedings of 2019 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS), pp. 339\u2013344 (2019). https:\/\/doi.org\/10.1109\/i2cacis.2019.8825004","DOI":"10.1109\/i2cacis.2019.8825004"},{"key":"2_CR19","doi-asserted-by":"publisher","unstructured":"AbdAlmisreb, A., Abidin, A.F., Tahir, N.M.: Maxout based deep neural networks for Arabic phonemes recognition. In: Proceedings of 2015 IEEE 11th International Colloquium on Signal Processing & Its Applications (CSPA), pp. 192\u2013197 (2015). https:\/\/doi.org\/10.1109\/cspa.2015.7225644","DOI":"10.1109\/cspa.2015.7225644"},{"key":"2_CR20","doi-asserted-by":"publisher","unstructured":"Emami, A., Mangu, L.: Empirical study of neural network language models for Arabic speech recognition. In: Proceedings of 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU), pp. 147\u2013152 (2007). https:\/\/doi.org\/10.1109\/asru.2007.4430100","DOI":"10.1109\/asru.2007.4430100"},{"key":"2_CR21","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1515\/comp-2019-0004","volume":"9","author":"N Zerari","year":"2019","unstructured":"Zerari, N., Abdelhamid, S., Bouzgou, H., Raymond, C.: Bidirectional deep architecture for Arabic speech recognition. Open Comput. Sci. 9, 92\u2013102 (2019). https:\/\/doi.org\/10.1515\/comp-2019-0004","journal-title":"Open Comput. Sci."},{"key":"2_CR22","doi-asserted-by":"publisher","unstructured":"Algihab, W., Alawwad, N., Aldawish, A., AlHumoud, S.: Arabic speech recognition with deep learning: a review. In: Proceedings of Social Computing and Social Media. Design, Human Behavior and Analytics, pp. 15\u201331 (2019). https:\/\/doi.org\/10.1007\/978-3-030-21902-4_2","DOI":"10.1007\/978-3-030-21902-4_2"},{"key":"2_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2020.e03372","volume":"6","author":"B Zada","year":"2020","unstructured":"Zada, B., Ullah, R.: Pashto isolated digits recognition using deep convolutional neural network. Heliyon 6, e03372 (2020). https:\/\/doi.org\/10.1016\/j.heliyon.2020.e03372","journal-title":"Heliyon"},{"key":"2_CR24","doi-asserted-by":"publisher","unstructured":"Choubassi, M.E., Khoury, H.E., Alagha, C., Skaf, J., Al-Alaoui, M.: Arabic speech recognition using recurrent neural networks. In: Proceedings of the 3rd IEEE International Symposium on Signal Processing and Information Technology (IEEE Cat. No. 03EX795), pp. 543\u2013547 (2003). https:\/\/doi.org\/10.1109\/isspit.2003.1341178","DOI":"10.1109\/isspit.2003.1341178"},{"key":"2_CR25","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/j.procs.2021.05.082","volume":"189","author":"A Messaoudi","year":"2021","unstructured":"Messaoudi, A., Haddad, H., Fourati, C., Hmida, M.B., Mabrouk, A.B.E., Graiet, M.: Tunisian dialectal end-to-end speech recognition based on DeepSpeech. Procedia Comput. Sci. 189, 183\u2013190 (2021). https:\/\/doi.org\/10.1016\/j.procs.2021.05.082","journal-title":"Procedia Comput. Sci."},{"key":"2_CR26","doi-asserted-by":"publisher","unstructured":"Ameen, Z.J.M., Kadhim, A.A.: Deep learning methods for Arabic autoencoder speech recognition system for electro-larynx device. In: Advances in Human-Computer Interaction, vol. 2023, pp. 1\u201311 (2023). https:\/\/doi.org\/10.1155\/2023\/7398538","DOI":"10.1155\/2023\/7398538"},{"key":"2_CR27","doi-asserted-by":"publisher","unstructured":"Mahmoudi, O., Bouami, M.F.: Arabic speech commands recognition with LSTM & GRU models using CUDA toolkit implementation. In: Proceedings of 2023 3rd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), pp. 1\u20134 (2023). https:\/\/doi.org\/10.1109\/iraset57153.2023.10152979","DOI":"10.1109\/iraset57153.2023.10152979"},{"key":"2_CR28","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., Mcleavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: Proceedings of the 40th International Conference on Machine Learning, vol. 202, pp. 28492\u201328518 (2023)"},{"key":"2_CR29","doi-asserted-by":"publisher","unstructured":"Zhang, Y., et al.: Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages. arXiv, vol. abs\/2303.01037 (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.01037","DOI":"10.48550\/arXiv.2303.01037"},{"key":"2_CR30","doi-asserted-by":"publisher","unstructured":"Wang, D., Wang, X., Lv, S.: An overview of end-to-end automatic speech recognition. Symmetry 11 (2019). https:\/\/doi.org\/10.3390\/sym11081018","DOI":"10.3390\/sym11081018"},{"key":"2_CR31","doi-asserted-by":"publisher","unstructured":"Olivier, R., Raj, B.: There is more than one kind of robustness: fooling whisper with adversarial examples. arXiv (2023). https:\/\/doi.org\/10.21437\/interspeech.2023-1105","DOI":"10.21437\/interspeech.2023-1105"},{"key":"2_CR32","doi-asserted-by":"publisher","unstructured":"Belinkov, Y., Ali, A., Glass, J.: Analyzing phonetic and graphemic representations in end-to-end automatic speech recognition. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, vol. 2019-September, pp. 81\u201385 (2019). https:\/\/doi.org\/10.21437\/interspeech.2019-2599","DOI":"10.21437\/interspeech.2019-2599"},{"key":"2_CR33","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.: Arabic speech recognition by end-to-end, modular systems and human. Comput. Speech Lang. 71, 101272 (2022). https:\/\/doi.org\/10.1016\/j.csl.2021.101272","journal-title":"Comput. Speech Lang."},{"key":"2_CR34","doi-asserted-by":"publisher","unstructured":"Chung, Y.A., et al.: w2v-BERT: combining contrastive learning and masked language modeling for self-supervised speech pre-training. In: Proceedings of 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 244\u2013250 (2021). https:\/\/doi.org\/10.1109\/asru51503.2021.9688253","DOI":"10.1109\/asru51503.2021.9688253"},{"key":"2_CR35","doi-asserted-by":"publisher","unstructured":"Conneau, A., et al.: FLEURS: FEW-shot learning evaluation of universal representations of speech. In: Proceedings of 2022 IEEE Spoken Language Technology Workshop (SLT), pp. 798\u2013805 (2023). https:\/\/doi.org\/10.1109\/slt54892.2023.10023141","DOI":"10.1109\/slt54892.2023.10023141"},{"key":"2_CR36","doi-asserted-by":"publisher","unstructured":"Martinez, J., Perez, H., Escamilla, E., Suzuki, M.M.: Speaker recognition using Mel frequency Cepstral Coefficients (MFCC) and Vector quantization (VQ) techniques. In: Proceedings of CONIELECOMP 2012, 22nd International Conference on Electrical Communications and Computers, pp. 248\u2013251 (2012). https:\/\/doi.org\/10.1109\/conielecomp.2012.6189918","DOI":"10.1109\/conielecomp.2012.6189918"},{"key":"2_CR37","doi-asserted-by":"publisher","unstructured":"H\u00f6nig, F., Stemmer, G., Hacker, C., Brugnara, F.: Revising perceptual linear prediction (PLP). In: Proceedings of Interspeech 2005, pp. 2997\u20133000 (2005). https:\/\/doi.org\/10.21437\/interspeech.2005-138","DOI":"10.21437\/interspeech.2005-138"},{"key":"2_CR38","unstructured":"Liu, G.K.: Evaluating Gammatone Frequency Cepstral Coefficients with Neural Networks for Emotion Recognition from Speech. arXiv, vol. abs\/1806.09010 (2018). https:\/\/api.semanticscholar.org\/CorpusID:49420993"},{"key":"2_CR39","doi-asserted-by":"publisher","unstructured":"Abushariah, M.A.M., Ainon, R.N., Zainuddin, R., Elshafei, M., Khalifa, O.O.: Natural speaker-independent Arabic speech recognition system based on Hidden Markov Models using Sphinx tools. In: Proceedings of International Conference on Computer and Communication Engineering (ICCCE 2010), pp. 1\u20136 (2010). https:\/\/doi.org\/10.1109\/iccce.2010.5556829","DOI":"10.1109\/iccce.2010.5556829"},{"key":"2_CR40","doi-asserted-by":"publisher","unstructured":"Povey, D., et al.: Subspace Gaussian mixture models for speech recognition. In: Proceedings of 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 4330\u20134333 (2010). https:\/\/doi.org\/10.1109\/icassp.2010.5495662","DOI":"10.1109\/icassp.2010.5495662"},{"key":"2_CR41","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"DE Rumelhart","year":"1986","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323, 533\u2013536 (1986). https:\/\/doi.org\/10.1038\/323533a0","journal-title":"Nature"},{"key":"2_CR42","doi-asserted-by":"publisher","unstructured":"Wang, Y., et al.: Transformer in action: a comparative study of transformer-based acoustic models for large scale speech recognition applications. In: Proceedings of ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6778\u20136782 (2021). https:\/\/doi.org\/10.1109\/icassp39728.2021.9414087","DOI":"10.1109\/icassp39728.2021.9414087"},{"key":"2_CR43","unstructured":"Huang, X., Acero, A., Hon, H.W., Reddy, R.: Spoken Language Processing: A Guide to Theory, Algorithm, and System Development (2001). https:\/\/ci.nii.ac.jp\/ncid\/BA52988971"},{"key":"2_CR44","doi-asserted-by":"publisher","unstructured":"Abdou, S.M., Moussa, A.M.: Arabic speech recognition: challenges and state of the art. In: Computational Linguistics, Speech and Image Processing for Arabic Language, pp. 1\u201327 (2018). https:\/\/doi.org\/10.1142\/9789813229396_0001","DOI":"10.1142\/9789813229396_0001"},{"key":"2_CR45","doi-asserted-by":"publisher","unstructured":"Masekwameng, M.S., Mokgonyane, T.B., Modipa, T.I., Manamela, M.J., Mogale, M.M.: Effects of language modelling for sepedi-english code-switched speech in automatic speech recognition system. In: Proceedings of 2020 International Conference on Artificial Intelligence, Big Data, Computing and Data Communication Systems (icABCD), pp. 1\u20135 (2020). https:\/\/doi.org\/10.1109\/icabcd49160.2020.9183865","DOI":"10.1109\/icabcd49160.2020.9183865"},{"key":"2_CR46","doi-asserted-by":"publisher","first-page":"467","DOI":"10.5555\/176313.176316","volume":"18","author":"PF Brown","year":"1992","unstructured":"Brown, P.F., deSouza, P.V., Mercer, R.L., Della Pietra, V.J., Lai, J.C.: Class-based n-gram models of natural language. Comput. Linguist. 18, 467\u2013479 (1992). https:\/\/doi.org\/10.5555\/176313.176316","journal-title":"Comput. Linguist."},{"key":"2_CR47","doi-asserted-by":"publisher","first-page":"3881","DOI":"10.4249\/scholarpedia.3881","volume":"3","author":"Y Bengio","year":"2008","unstructured":"Bengio, Y.: Neural net language models. Scholarpedia 3, 3881 (2008). https:\/\/doi.org\/10.4249\/scholarpedia.3881","journal-title":"Scholarpedia"},{"key":"2_CR48","unstructured":"Zheng, O., Abdel-Aty, M., Wang, D., Wang, Z., Ding, S.: ChatGPT is on the Horizon: Could a Large Language Model be Suitable for Intelligent Traffic Safety Research and Applications? arxiv (2023). https:\/\/api.semanticscholar.org\/CorpusID:261557640"},{"key":"2_CR49","unstructured":"Harere, A.A., Jallad, K.A.: Quran Recitation Recognition using End-to-End Deep Learning. arXiv, vol. abs\/2305.07034 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258676128"},{"key":"2_CR50","doi-asserted-by":"publisher","unstructured":"Biswas, D., Nadipalli, S., Sneha, B., Supriya, M.: Speech recognition using weighted finite-state transducers. In: Proceedings of 2022 IEEE 7th International Conference for Convergence in Technology (I2CT), pp. 1\u20135 (2022). https:\/\/doi.org\/10.1109\/i2ct54291.2022.9824703","DOI":"10.1109\/i2ct54291.2022.9824703"},{"key":"2_CR51","doi-asserted-by":"crossref","unstructured":"Ali, A.M., et al.: The MGB-2 challenge: Arabic multi-dialect broadcast media recognition. In: Proceedings of 2016 IEEE Spoken Language Technology Workshop (SLT), pp. 279\u2013284 (2016). https:\/\/api.semanticscholar.org\/CorpusID:9163450","DOI":"10.1109\/SLT.2016.7846277"},{"key":"2_CR52","doi-asserted-by":"publisher","unstructured":"Ali, A., Vogel, S., Renals, S.: Speech recognition challenge in the wild: Arabic MGB-3. In: Proceedings of 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 316\u2013322 (2017). https:\/\/doi.org\/10.1109\/ASRU.2017.8268952","DOI":"10.1109\/ASRU.2017.8268952"},{"key":"2_CR53","doi-asserted-by":"publisher","unstructured":"Al-Fetyani, M., Al-Barham, M., Abandah, G., Alsharkawi, A., Dawas, M.: MASC: massive Arabic speech corpus. In: Proceedings of 2022 IEEE Spoken Language Technology Workshop (SLT), pp. 1006\u20131013 (2023). https:\/\/doi.org\/10.1109\/slt54892.2023.10022652","DOI":"10.1109\/slt54892.2023.10022652"},{"key":"2_CR54","unstructured":"CALLHOME Egyptian Arabic Speech. https:\/\/catalog.ldc.upenn.edu\/LDC97S45"},{"key":"2_CR55","unstructured":"Kolobov, R., et al.: MediaSpeech: Multilanguage ASR Benchmark and Dataset. arXiv, vol. abs\/2103.16193 (2021). https:\/\/api.semanticscholar.org\/CorpusID:232417874"},{"key":"2_CR56","unstructured":"Alghmadi, M.M., Abdulaziz, K.: KACST Arabic Phonetics Database (2003). https:\/\/api.semanticscholar.org\/CorpusID:40304009"},{"key":"2_CR57","unstructured":"B-Ubuntu, openSLR: Quran Ayat Speech to Text (2022). https:\/\/www.kaggle.com\/datasets\/bigguyubuntu\/quran-ayat-speech-to-text"},{"key":"2_CR58","doi-asserted-by":"publisher","unstructured":"Bahi, H., Sellami, M.: Combination of vector quantization and hidden Markov models for Arabic speech recognition. In: Proceedings ACS\/IEEE International Conference on Computer Systems and Applications, pp. 96\u2013100 (2002). https:\/\/doi.org\/10.1109\/aiccsa.2001.933957","DOI":"10.1109\/aiccsa.2001.933957"},{"key":"2_CR59","doi-asserted-by":"publisher","unstructured":"Bourouba, H., Djemili, R., Bedda, M., Snani, C.: New hybrid system (supervised classifier\/HMM) for isolated Arabic speech recognition. In: Proceedings of 2006 2nd International Conference on Information & Communication Technologies, pp. 1264\u20131269 (2006). https:\/\/doi.org\/10.1109\/ICTTA.2006.1684560","DOI":"10.1109\/ICTTA.2006.1684560"},{"key":"2_CR60","doi-asserted-by":"publisher","unstructured":"Walker, K., Christopher, C., Kazuaki, M., Denise, D., Stephanie, S.: GALE phase 2 Arabic broadcast news speech part 1 LDC2014S07. In: Philadelphia: Linguistic Data Consortium (2014). https:\/\/doi.org\/10.35111\/2ryw-sp19","DOI":"10.35111\/2ryw-sp19"},{"key":"2_CR61","doi-asserted-by":"publisher","unstructured":"Glenn, M., Haejoong, L., Stephanie, S., Kazuaki, M.: GALE phase 3 Arabic broadcast news transcripts part 1 LDC2016T17. In: Philadelphia: Linguistic Data Consortium (2016). https:\/\/doi.org\/10.35111\/vn1b-an41","DOI":"10.35111\/vn1b-an41"},{"key":"2_CR62","doi-asserted-by":"publisher","unstructured":"Ali, A., Renals, S.: Word error rate estimation for speech recognition: e-WER. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, vol. 2, pp. 20\u201324 (2018). https:\/\/doi.org\/10.18653\/v1\/p18-2004","DOI":"10.18653\/v1\/p18-2004"},{"key":"2_CR63","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1109\/34.771314","volume":"21","author":"I Bazzi","year":"1999","unstructured":"Bazzi, I., Schwartz, R., Makhoul, J.: An omnifont open-vocabulary OCR system for English and Arabic. IEEE Trans. Pattern Anal. Mach. Intell. 21, 495\u2013504 (1999). https:\/\/doi.org\/10.1109\/34.771314","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR64","doi-asserted-by":"publisher","unstructured":"Stolcke, A., Konig, Y., Weintraub, M.: Explicit word error minimization in n-best list rescoring. In: Proceedings of EUROSPEECH (1997). https:\/\/doi.org\/10.21437\/eurospeech.1997-68","DOI":"10.21437\/eurospeech.1997-68"},{"key":"2_CR65","doi-asserted-by":"publisher","unstructured":"Mubarak, H., Hussein, A., Chowdhury, S.A., Ali, A.: QASR: QCRI aljazeera speech resource a large scale annotated arabic speech corpus. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 2274\u20132285 (2021). https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.177","DOI":"10.18653\/v1\/2021.acl-long.177"}],"container-title":["Lecture Notes in Networks and Systems","Advances in Information and Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-85363-0_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T08:51:03Z","timestamp":1741078263000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-85363-0_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031853623","9783031853630"],"references-count":65,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-85363-0_2","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"value":"2367-3370","type":"print"},{"value":"2367-3389","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"5 March 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"FICC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Future of Information and Communication Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Berlin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 April 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 April 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ficc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/saiconference.com\/FICC","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}