{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T15:40:03Z","timestamp":1785858003469,"version":"3.56.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"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":[[2024,12]]},"DOI":"10.1007\/s10772-024-10154-0","type":"journal-article","created":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T16:03:10Z","timestamp":1730217790000},"page":"1121-1133","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Comparative study of CNN, LSTM and hybrid CNN-LSTM model in amazigh speech recognition using spectrogram feature extraction and different gender and age dataset"],"prefix":"10.1007","volume":"27","author":[{"given":"Meryam","family":"Telmem","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naouar","family":"Laaidi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youssef","family":"Ghanou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanae","family":"Hamiane","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hassan","family":"Satori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"issue":"1","key":"10154_CR1","doi-asserted-by":"publisher","first-page":"27","DOI":"10.21608\/ejle.2020.47685.1015","volume":"8","author":"ER Abdelmaksoud","year":"2021","unstructured":"Abdelmaksoud, E. R., Hassen, A., Hassan, N., & Hesham, M. (2021). Convolutional neural network for Arabic speech recognition. The Egyptian Journal of Language Engineering, 8(1), 27\u201338.","journal-title":"The Egyptian Journal of Language Engineering"},{"issue":"1","key":"10154_CR2","doi-asserted-by":"publisher","first-page":"563","DOI":"10.11591\/ijai.v13.i1.pp563-571","volume":"13","author":"AQ Albayati","year":"2024","unstructured":"Albayati, A. Q., Altaie, S. A. J., Al-Obaydy, W. N. I., & Alkhalid, F. F. (2024). Performance analysis of optimization algorithms for convolutional neural network-based handwritten digit recognition. IAES International Journal of Artificial Intelligence (IJ-AI), 13(1), 563\u2013571.","journal-title":"IAES International Journal of Artificial Intelligence (IJ-AI)"},{"key":"10154_CR3","doi-asserted-by":"crossref","unstructured":"Ali, A.R. (2020). Multi-dialect Arabic speech recognition. In 2020 international joint conference on neural networks (IJCNN) (pp. 1\u20137). IEEE.","DOI":"10.1109\/IJCNN48605.2020.9206658"},{"key":"10154_CR4","doi-asserted-by":"publisher","first-page":"57063","DOI":"10.1109\/ACCESS.2022.3177191","volume":"10","author":"HA Alsayadi","year":"2022","unstructured":"Alsayadi, H. A., Abdelhamid, A. A., Hegazy, I., Alotaibi, B., & Fayed, Z. T. (2022). Deep investigation of the recent advances in dialectal Arabic speech recognition. IEEE Access, 10, 57063\u201357079.","journal-title":"IEEE Access"},{"issue":"8","key":"10154_CR5","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. (2021a). Arabic speech recognition using end-to-end deep learning. IET Signal Processing, 15(8), 521\u2013534.","journal-title":"IET Signal Processing"},{"issue":"6","key":"10154_CR6","doi-asserted-by":"publisher","first-page":"6207","DOI":"10.3233\/JIFS-202841","volume":"41","author":"HA Alsayadi","year":"2021","unstructured":"Alsayadi, H. A., Abdelhamid, A. A., Hegazy, I., & Fayed, Z. T. (2021b). Non-diacritized Arabic speech recognition based on CNN-LSTM and attention-based models. Journal of Intelligent & Fuzzy Systems, 41(6), 6207\u20136621.","journal-title":"Journal of Intelligent & Fuzzy Systems"},{"issue":"1","key":"10154_CR7","first-page":"400","volume":"13","author":"ZJM Ameen","year":"2023","unstructured":"Ameen, Z. J. M., & Kadhim, A. A. (2023). Machine learning for Arabic phonemes recognition using electrolarynx speech. International Journal of Electrical and Computer Engineering, 13(1), 400.","journal-title":"International Journal of Electrical and Computer Engineering"},{"key":"10154_CR8","volume-title":"Initiation la langue amazigh","author":"M Ameur","year":"2004","unstructured":"Ameur, M., Bouhjar, A., & Boukhris, F. (2004). Initiation la langue Amazigh. Institut Royal de la Culture Amazighe."},{"key":"10154_CR9","doi-asserted-by":"crossref","unstructured":"Astuti, Y., Hidayat, R., & Bejo, A. (2022). A mel-weighted spectrogram feature extraction for improved speaker recognition system. International Journal of Intelligent Engineering & Systems, 15(6).","DOI":"10.22266\/ijies2022.1231.08"},{"key":"10154_CR10","doi-asserted-by":"crossref","unstructured":"Badshah, A. M., Ahmad, J., Rahim, N., & Baik, S. W. (2017). Speech emotion recognition from spectrograms with deep convolutional neural network. In 2017 international conference on platform technology and service (PlatCon) (pp. 1\u20135). IEEE.","DOI":"10.1109\/PlatCon.2017.7883728"},{"key":"10154_CR11","unstructured":"Bhatta, B., Joshi, B., & Maharjhan, R. K. (2020, September). Nepali speech recognition using CNN, GRU, and CTC. In Proceedings of the 32nd conference on computational linguistics and speech processing (ROCLING 2020) (pp. 238\u2013246)."},{"issue":"7","key":"10154_CR13","doi-asserted-by":"publisher","first-page":"791","DOI":"10.32985\/ijeces.14.7.6","volume":"14","author":"H Boulal","year":"2023","unstructured":"Boulal, H., Hamidi, M., Abarkan, M., & Barkani, J. (2023). Amazigh spoken digit recognition using a deep learning approach based on MFCC. International Journal of Electrical and Computer Engineering Systems, 14(7), 791\u2013798.","journal-title":"International Journal of Electrical and Computer Engineering Systems"},{"key":"10154_CR12","doi-asserted-by":"crossref","unstructured":"Boulal, H., Hamidi, M., Abarkan, M., & Barkani, J. (2024). Amazigh CNN speech recognition system based on Mel spectrogram feature extraction method. International Journal of Speech Technology, 27(1), 287\u2013296.","DOI":"10.1007\/s10772-024-10100-0"},{"issue":"3","key":"10154_CR14","doi-asserted-by":"publisher","first-page":"775","DOI":"10.1007\/s10772-023-10054-9","volume":"26","author":"M Daouad","year":"2023","unstructured":"Daouad, M., Allah, F. A., & Dadi, E. W. (2023). An automatic speech recognition system for isolated Amazigh word using 1D & 2D CNN-LSTM architecture. International Journal of Speech Technology, 26(3), 775\u2013787.","journal-title":"International Journal of Speech Technology"},{"issue":"3","key":"10154_CR15","first-page":"853","volume":"29","author":"S Hamiane","year":"2024","unstructured":"Hamiane, S., Ghanou, Y., Khalifi, H., & Telmem, M. (2024). Comparative analysis of LSTM, ARIMA, and hybrid models for forecasting future GDP. Ingenierie des Systemes d\u2019information, 29(3), 853\u2013861.","journal-title":"Ingenierie des Systemes d'information"},{"key":"10154_CR16","doi-asserted-by":"crossref","unstructured":"Han, W., Zhang, Z., Zhang, Y., Yu, J., Chiu, C. C., Qin, J., Wu, Y. (2020). ContextNet: Improving convolutional neural networks for automatic speech recognition with global context. arXiv:2005.03191","DOI":"10.21437\/Interspeech.2020-2059"},{"key":"10154_CR17","doi-asserted-by":"crossref","unstructured":"Hou, Y., Kong, Q., & Li, S. (2018). Audio tagging with connectionist temporal classification model using sequentially labelled data. In International conference in communications, signal processing, and systems (pp. 955\u2013964). Springer.","DOI":"10.1007\/978-981-13-6504-1_114"},{"key":"10154_CR18","unstructured":"Huzaifah, M. (2017). Comparison of time-frequency representations for environmental sound classification using convolutional neural networks. arXiv preprint arXiv:1706.07156"},{"key":"10154_CR20","unstructured":"Liu, X. (2018). Deep convolutional and LSTM neural networks for acoustic modelling in automatic speech recognition."},{"issue":"3","key":"10154_CR21","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. (2021). A comparative study for Arabic speech recognition system in noisy environments. International Journal of Speech Technology, 24(3), 761\u2013770.","journal-title":"International Journal of Speech Technology"},{"key":"10154_CR22","doi-asserted-by":"crossref","unstructured":"Ramasubramanian, K., & Singh, A. (2019). Deep learning using Keras and TensorFlow. In *Machine Learning Using R* (pp. 667\u2013688). Apress","DOI":"10.1007\/978-1-4842-4215-5_11"},{"key":"10154_CR23","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1007\/s10772-014-9223-y","volume":"17","author":"H Satori","year":"2014","unstructured":"Satori, H., & ElHaoussi, F. (2014). Investigation Amazigh speech recognition using CMU tools. International Journal of Speech Technology, 17, 235\u2013243.","journal-title":"International Journal of Speech Technology"},{"key":"10154_CR25","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.procs.2018.01.102","volume":"127","author":"M Telmem","year":"2018","unstructured":"Telmem, M., & Ghanou, Y. (2018). Estimation of the optimal HMM parameters for amazigh speech recognition system using CMU-sphinx. Procedia Computer Science, 127, 92\u2013101.","journal-title":"Procedia Computer Science"},{"key":"10154_CR24","doi-asserted-by":"crossref","unstructured":"Telmem, M., & Ghanou, Y. (2020). A comparative study of HMMs and CNN acoustic models in the Amazigh recognition system. In *Embedded systems and artificial intelligence: Proceedings of ESAI 2019* (pp. 533\u2013540). Springer.","DOI":"10.1007\/978-981-15-0947-6_50"},{"issue":"2","key":"10154_CR26","doi-asserted-by":"publisher","first-page":"515","DOI":"10.12928\/telkomnika.v19i2.16793","volume":"19","author":"M Telmem","year":"2021","unstructured":"Telmem, M., & Ghanou, Y. (2021). The convolutional neural networks for Amazigh speech recognition system. TELKOMNIKA (Telecommunication Computing Electronics and Control), 19(2), 515\u2013522.","journal-title":"TELKOMNIKA (Telecommunication Computing Electronics and Control)"},{"key":"10154_CR27","unstructured":"TensorFlow. Audio recognition tutorial. Retrieved from https:\/\/www.tensorflow.org\/tutorials\/sequences\/audio_recognition"},{"key":"10154_CR28","unstructured":"TensorFlow. Install TensorFlow. Retrieved from https:\/\/www.tensorflow.org\/install\/"},{"key":"10154_CR29","unstructured":"The corpus was provided in 2014 through collaboration with Professor Hassan Satori\u2019s team,titled Intelligence Artificielle, Systems Complexes et Mod\u00e9lisation (IASCM), from the Facutlty of Polydicsiplinary in Nador, Mohmed First University."},{"key":"10154_CR30","doi-asserted-by":"crossref","unstructured":"Wang, Q., & Chu, X. (2017). GPGPU performance estimation with core and memory frequency scaling. arXiv preprint arXiv:1701.05308","DOI":"10.1145\/3152042.3152066"},{"issue":"1","key":"10154_CR31","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1007\/s10772-017-9487-0","volume":"21","author":"O Zealouk","year":"2018","unstructured":"Zealouk, O., Satori, H., Hamidi, M., Laaidi, N., & Satori, K. (2018). Vocal parameters analysis of smoker using Amazigh language. International Journal of Speech Technology, 21(1), 85\u201391.","journal-title":"International Journal of Speech Technology"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-024-10154-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-024-10154-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-024-10154-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T10:10:11Z","timestamp":1734343811000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-024-10154-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"references-count":30,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["10154"],"URL":"https:\/\/doi.org\/10.1007\/s10772-024-10154-0","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"30 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 September 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 October 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 that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}