{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T12:50:07Z","timestamp":1765889407322,"version":"3.40.4"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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":[[2025,3]]},"DOI":"10.1007\/s10772-024-10158-w","type":"journal-article","created":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T14:06:10Z","timestamp":1730469970000},"page":"27-37","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Optimizing Whisper models for Amazigh ASR: a comparative analysis"],"prefix":"10.1007","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6492-2513","authenticated-orcid":false,"given":"Mohamed","family":"Daouad","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7091-4412","authenticated-orcid":false,"given":"Fadoua","family":"Ataa Allah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2946-854X","authenticated-orcid":false,"given":"El Wardani","family":"Dadi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"10158_CR1","doi-asserted-by":"publisher","unstructured":"Abakarim, F., & Abenaou, A. (2020). Amazigh isolated word speech recognition system using the adaptive orthogonal transform method. In 2020 international conference on intelligent systems and computervision (ISCV 2020). https:\/\/doi.org\/10.1109\/ISCV49265.2020.9204291","DOI":"10.1109\/ISCV49265.2020.9204291"},{"key":"10158_CR2","first-page":"1","volume":"2020-Decem(Fig.","author":"A Baevski","year":"2020","unstructured":"Baevski, A., Zhou, H., Mohamed, A., & Auli, M. (2020). wav2vec 2.0: A framework for self-supervised learning of speech representations. In Advances in neural information processing systems, 2020-Decem(Fig. 1), (pp. 1\u201312).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10158_CR3","doi-asserted-by":"publisher","unstructured":"Barkani, F., Hamidi, M., Laaidi, N., Zealouk, O., Satori, H., & Satori, K. (2023). Amazigh speech recognition based on the Kaldi ASR toolkit. International Journal of Information Technology (Singapore), 0123456789. https:\/\/doi.org\/10.1007\/s41870-023-01354-z","DOI":"10.1007\/s41870-023-01354-z"},{"issue":"1","key":"10158_CR4","first-page":"59","volume":"4","author":"K Bensoukas","year":"2018","unstructured":"Bensoukas, K. (2018). Concurrent cognate and contact-induced plural traits in Afro-Asiatic: Amazigh id-and arabic-at plurals *. The International Journal of Arabic Linguistics, 4(1), 59\u2013102.","journal-title":"The International Journal of Arabic Linguistics (IJAL)"},{"issue":"1","key":"10158_CR5","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1007\/s10772-024-10100-0","volume":"27","author":"H Boulal","year":"2024","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. https:\/\/doi.org\/10.1007\/s10772-024-10100-0","journal-title":"International Journal of Speech Technology"},{"issue":"1","key":"10158_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3607720.3607760","volume":"1","author":"M Daouad","year":"2023","unstructured":"Daouad, M., & Dadi, E. W. (2023). Amazigh speech recognition using 1D CNN. Proceedings of the 6th International Conference on Networking Intelligent Systems & Security, 1(1), 1\u20136. https:\/\/doi.org\/10.1145\/3607720.3607760","journal-title":"Proceedings of the 6th International Conference on Networking Intelligent Systems & Security"},{"issue":"3","key":"10158_CR6","doi-asserted-by":"publisher","first-page":"775","DOI":"10.1007\/s10772-023-10054-9","volume":"26","author":"M Daouad","year":"2023","unstructured":"Daouad, M., Ataa Allah, F., & 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. https:\/\/doi.org\/10.1007\/s10772-023-10054-9","journal-title":"International Journal of Speech Technology"},{"key":"10158_CR7","doi-asserted-by":"crossref","unstructured":"Daouad, M., Ataa Allah, F., & Dadi, E. W. (2024). Amazigh speech recognition via parallel CNN transformer-encoder model. In Proceedings of the 2nd edition of the hybrid international conference on artificial intelligence and applied mathematics (JIAMA24). unpublished.","DOI":"10.1007\/978-3-031-75329-9_28"},{"key":"10158_CR9","unstructured":"Devlin, J., Chang, M. W., Lee, K., T. K., & Google, A. I. (2018). Language BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT 2019, (pp. 4171\u20134186). https:\/\/aclanthology.org\/N19-1423.pdf"},{"key":"10158_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/CloudTech.2017.8284715","volume":"2018-Janua","author":"S El Ouahabi","year":"2018","unstructured":"El Ouahabi, S., Atounti, M., & Bellouki, M. (2018). A database for Amazigh speech recognition research: AMZSRD. In Proceedings of 2017 international conference of cloud computing technologies and applications (cloudtech 2017), 2018-Janua, (pp. 1\u20135). https:\/\/doi.org\/10.1109\/CloudTech.2017.8284715","journal-title":"Proceedings of 2017 International Conference of Cloud Computing Technologies and Applications CloudTech 2017"},{"issue":"2","key":"10158_CR11","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1007\/s10772-019-09617-6","volume":"22","author":"S El Ouahabi","year":"2019","unstructured":"El Ouahabi, S., Atounti, M., & Bellouki, M. (2019). Toward an automatic speech recognition system for Amazigh-Tarifit language. International Journal of Speech Technology, 22(2), 421\u2013432. https:\/\/doi.org\/10.1007\/s10772-019-09617-6","journal-title":"International Journal of Speech Technology"},{"issue":"4","key":"10158_CR12","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1007\/s10772-020-09762-3","volume":"23","author":"S El Ouahabi","year":"2020","unstructured":"El Ouahabi, S., Atounti, M., & Bellouki, M. (2020). Optimal parameters selected for automatic recognition of spoken Amazigh digits and letters using hidden Markov model toolkit. International Journal of Speech Technology, 23(4), 861\u2013871. https:\/\/doi.org\/10.1007\/s10772-020-09762-3","journal-title":"International Journal of Speech Technology"},{"key":"10158_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.engappai.2021.104267","volume":"102","author":"A Ghandoura","year":"2021","unstructured":"Ghandoura, A., Hjabo, F., & Al Dakkak, O. (2021). Building and benchmarking an Arabic speech commands dataset for small-footprint keyword spotting. Engineering Applications of Artificial Intelligence, 102, 1\u201318. https:\/\/doi.org\/10.1016\/j.engappai.2021.104267","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10158_CR14","doi-asserted-by":"publisher","first-page":"5036","DOI":"10.21437\/Interspeech.2020-3015","volume":"2020-Octob","author":"A Gulati","year":"2020","unstructured":"Gulati, A., Qin, J., Chiu, C. C., Parmar, N., Zhang, Y., Yu, J., Han, W., Wang, S., Zhang, Z., Wu, Y., & Pang, R. (2020). Conformer: Convolution-augmented transformer for speech recognition. In Proceedings of the annual conference of the international speech communication association (INTERSPEECH 2020), (pp. 5036\u20135040). https:\/\/doi.org\/10.21437\/Interspeech.2020-3015","journal-title":"Proceedings of the Annual Conference of the International Speech Communication Association INTERSPEECH"},{"issue":"1","key":"10158_CR15","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","volume":"45","author":"K Han","year":"2023","unstructured":"Han, K., Wang, Y., Chen, H., Chen, X., Guo, J., Liu, Z., Tang, Y., Xiao, A., Xu, C., Xu, Y., Yang, Z., Zhang, Y., & Tao, D. (2023). A survey on vision transformer. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(1), 87\u2013110. https:\/\/doi.org\/10.1109\/TPAMI.2022.3152247","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10158_CR16","doi-asserted-by":"publisher","unstructured":"Hsu, W. N., Tsai, Y. H. H., Bolte, B., Salakhutdinov, R., & Mohamed, A. (2021). Hubert: How much can a bad teacher benefit ASR pre-training? In  IEEE international conference on acoustics, speech and signal processing - Proceedings, (ICASSP 2021)-, (pp. 6533\u20136537). https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9414460","DOI":"10.1109\/ICASSP39728.2021.9414460"},{"issue":"3","key":"10158_CR17","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1080\/13629387.2019.1690996","volume":"26","author":"A Idhssaine","year":"2021","unstructured":"Idhssaine, A., & El Kirat, Y. (2021). Amazigh language use, perceptions and revitalisation in Morocco: The case of Rabat-Sale region. Journal of North African Studies, 26(3), 465\u2013479. https:\/\/doi.org\/10.1080\/13629387.2019.1690996","journal-title":"Journal of North African Studies"},{"key":"10158_CR18","doi-asserted-by":"publisher","first-page":"5242","DOI":"10.21437\/Interspeech.2023-935","volume":"2023-Augus","author":"R Jain","year":"2023","unstructured":"Jain, R., Barcovschi, A., Yiwere, M., Corcoran, P., & Cucu, H. (2023). Adaptation of Whisper models to child speech recognition. In Proceedings of the annual conference of the international speech communication association (INTERSPEECH 2023), (pp. 5242\u20135246). https:\/\/doi.org\/10.21437\/Interspeech.2023-935","journal-title":"Proceedings of the Annual Conference of the International Speech Communication Association INTERSPEECH"},{"key":"10158_CR19","unstructured":"Kadl\u010d\u00edk, M., H\u00e1jek, A., Kieslich, J., & Winiecki, R. (2023). A Whisper transformer for audio captioning trained with synthetic captions and transfer learning. http:\/\/arxiv.org\/abs\/2305.09690"},{"issue":"4","key":"10158_CR20","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1109\/ASRU46091.2019.9003750","volume":"9","author":"S Karita","year":"2019","unstructured":"Karita, S., Wang, X., Watanabe, S., Yoshimura, T., Zhang, W., Chen, N., Hayashi, T., Hori, T., Inaguma, H., Jiang, Z., Someki, M., Soplin, N. E. Y., & Yamamoto, R. (2019). A comparative study on transformer vs RNN in speech applications. In 2019 IEEE automatic speech recognition and understanding workshop (ASRU 2019 ) - Proceedings, 9(4), 449\u2013456. https:\/\/doi.org\/10.1109\/ASRU46091.2019.9003750","journal-title":"2019 IEEE Automatic Speech Recognition and Understanding Workshop ASRU 2019 - Proceedings"},{"key":"10158_CR21","doi-asserted-by":"publisher","unstructured":"Kriman, S., Beliaev, S., Ginsburg, B., Huang, J., Kuchaiev, O., Lavrukhin, V., Leary, R., Li, J., & Zhang, Y. (2020). Quartznet: Deep automatic speech recognition with 1D time-channel separable convolutions. In IEEE international conference on acoustics, speech and signal processing - Proceedings (ICASSP 2020), (pp. 6124\u20136128). https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9053889","DOI":"10.1109\/ICASSP40776.2020.9053889"},{"key":"10158_CR22","doi-asserted-by":"publisher","unstructured":"Liu, Y., Yang, X., & Qu, D. (2024). Exploration of Whisper fine-tuning strategies for low-resource ASR. Eurasip Journal on Audio Speech and Music Processing, 2024(1). https:\/\/doi.org\/10.1186\/s13636-024-00349-3","DOI":"10.1186\/s13636-024-00349-3"},{"key":"10158_CR23","unstructured":"Majumdar, S., Balam, J., Hrinchuk, O., Lavrukhin, V., Noroozi, V., & Ginsburg, B. (2021). Citrinet: Closing the gap between non-autoregressive and autoregressive end-to-end models for automatic speech recognition. (pp. 1\u20135). http:\/\/arxiv.org\/abs\/2104.01721"},{"issue":"2","key":"10158_CR24","doi-asserted-by":"publisher","first-page":"413","DOI":"10.14569\/IJACSA.2023.0140250","volume":"14","author":"A Ouhnini","year":"2023","unstructured":"Ouhnini, A., Aksasse, B., & Ouanan, M. (2023). Towards an automatic speech-to-text transcription system: Amazigh language. International Journal of Advanced Computer Science and Applications, 14(2), 413\u2013418. https:\/\/doi.org\/10.14569\/IJACSA.2023.0140250","journal-title":"International Journal of Advanced Computer Science and Applications"},{"key":"10158_CR26","unstructured":"Pratap, V., Tjandra, A., Shi, B., Tomasello, P., Babu, A., Kundu, S., Elkahky, A., Ni, Z., Vyas, A., Fazel-Zarandi, M., Baevski, A., Adi, Y., Zhang, X., Hsu, W. N., Conneau, A., & Auli, M. (2023). Scaling speech technology to 1,000\u2009+\u2009Languages. http:\/\/arxiv.org\/abs\/2305.13516."},{"key":"10158_CR27","first-page":"28492","volume":"202","author":"A Radford","year":"2023","unstructured":"Radford, A., Kim, J. W., Xu, T., Brockman, G., McLeavey, C., & Sutskever, I. (2023). Robust speech recognition via large-scale weak supervision. Proceedings of Machine Learning Research, 202, 28492\u201328518.","journal-title":"Proceedings of Machine Learning Research"},{"issue":"3","key":"10158_CR28","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(3), 235\u2013243. https:\/\/doi.org\/10.1007\/s10772-014-9223-y","journal-title":"International Journal of Speech Technology"},{"key":"10158_CR29","unstructured":"Sicard, C., Z\u00fcrich, E., Gillioz, V., & Pyszkowski, K. (2023). Spaiche: Extending state-of-the-art ASR models to Swiss German dialects. https:\/\/www.speechmatics"},{"key":"10158_CR30","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1007\/978-981-15-0947-6_50","volume":"1076","author":"M Telmem","year":"2020","unstructured":"Telmem, M., & Ghanou, Y. (2020). A comparative study of HMMs and CNN acoustic model in Amazigh recognition system. Advances in Intelligent Systems and Computing, 1076, 533\u2013540. https:\/\/doi.org\/10.1007\/978-981-15-0947-6_50","journal-title":"Advances in Intelligent Systems and Computing"},{"issue":"2","key":"10158_CR31","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. https:\/\/doi.org\/10.12928\/TELKOMNIKA.v19i2.16793","journal-title":"Telkomnika (Telecommunication Computing Electronics and Control)"},{"key":"10158_CR32","doi-asserted-by":"publisher","unstructured":"V\u00e1squez-Correa, J. C., & \u00c1lvarez Muniain, A. (2023). Novel speech recognition systems applied to forensics within child exploitation: Wav2vec2.0 vs. Whisper Sensors, 23(4). https:\/\/doi.org\/10.3390\/s23041843","DOI":"10.3390\/s23041843"},{"key":"10158_CR33","doi-asserted-by":"crossref","unstructured":"Waheed, A., Talafha, B., Sullivan, P., Elmadany, A. R., & Abdul-Mageed, M. (2023). A robust dialect-aware Arabic speech recognition system. In ArabicNLP 2023\u20131st Arabic natural language processing conference, proceedings, (pp. 441\u2013449).","DOI":"10.18653\/v1\/2023.arabicnlp-1.38"},{"key":"10158_CR34","doi-asserted-by":"publisher","first-page":"770","DOI":"10.21437\/Interspeech.2023-1505","volume":"2023-Augus(Augu","author":"M Wang","year":"2023","unstructured":"Wang, M., Li, Y., Guo, J., Qiao, X., Li, Z., Shang, H., Wei, D., Tao, S., Zhang, M., & Yang, H. (2023). WhiSLU: End-to-end spoken language understanding with Whisper. In Proceedings of the annual conference of the international speech communication association (INTERSPEECH 2023), (pp. 770\u2013774). https:\/\/doi.org\/10.21437\/Interspeech.2023-1505","journal-title":"Proceedings of the Annual Conference of the International Speech Communication Association INTERSPEECH"},{"key":"10158_CR35","doi-asserted-by":"publisher","unstructured":"Williams, A., Demarco, A., & Borg, C. (2023). The applicability of Wav2Vec2 and Whisper for low-resource Maltese ASR. August, 39\u201343. https:\/\/doi.org\/10.21437\/sigul.2023-9","DOI":"10.21437\/sigul.2023-9"},{"key":"10158_CR36","unstructured":"Xie, P., & Chen, K. (2023). MADGF: Multi-agent data generation framework. http:\/\/arxiv.org\/abs\/2310.17953"},{"key":"10158_CR37","doi-asserted-by":"crossref","unstructured":"Yang, Y., Peng, Y., Zhong, X., Huang, H., & Chng, E. S. (2023). Adapting OpenAI\u2019s Whisper for speech recognition on code-switch Mandarin-English SEAME and ASRU2019 Datasets. (pp. 1\u20136). http:\/\/arxiv.org\/abs\/2311.17382","DOI":"10.1109\/APSIPAASC63619.2025.10849308"},{"key":"10158_CR25","doi-asserted-by":"crossref","unstructured":"Zealouk, O., Satori, H., Hamidi, M., & Satori, K. (2019). Pathological detection using HMM speech recognition-based Amazigh digits. Embedded Systems and Artificial Intelligence, 281\u2013289.","DOI":"10.1007\/978-981-15-0947-6_27"},{"issue":"4","key":"10158_CR38","doi-asserted-by":"publisher","first-page":"885","DOI":"10.1007\/s10772-020-09764-1","volume":"23","author":"O Zealouk","year":"2020","unstructured":"Zealouk, O., Satori, H., Laaidi, N., Hamidi, M., & Satori, K. (2020). Noise effect on Amazigh digits in speech recognition system. International Journal of Speech Technology, 23(4), 885\u2013892. https:\/\/doi.org\/10.1007\/s10772-020-09764-1","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\/s10772-024-10158-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-024-10158-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-024-10158-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T08:52:12Z","timestamp":1744275132000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-024-10158-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["10158"],"URL":"https:\/\/doi.org\/10.1007\/s10772-024-10158-w","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"2 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 November 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 they have no financial interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}