{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T23:04:01Z","timestamp":1772060641421,"version":"3.50.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T00:00:00Z","timestamp":1771977600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T00:00:00Z","timestamp":1771977600000},"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":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-026-21336-0","type":"journal-article","created":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T22:33:09Z","timestamp":1772058789000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient fine-tuning of whisper models for Amazigh ASR: leveraging LoRA and its variants"],"prefix":"10.1007","volume":"85","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":[[2026,2,25]]},"reference":[{"key":"21336_CR1","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. Int J Speech Technol 23:861\u2013871. https:\/\/doi.org\/10.1007\/s10772-020-09762-3","journal-title":"Int J Speech Technol"},{"key":"21336_CR2","doi-asserted-by":"crossref","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. pp. 1\u20135","DOI":"10.1109\/CloudTech.2017.8284715"},{"key":"21336_CR3","doi-asserted-by":"publisher","unstructured":"Daouad M, Ataa Allah F, Dadi EW (2025) Impact of spectrogram resizing for automatic speech recognition case of amazigh isolated word. In: Proceeding 4th\u00a0International Conference on Intelligent Systems and Advanced Computing Sciences, pp 183\u2013194. ISACS\u201923. https:\/\/doi.org\/10.1007\/978-3-031-93448-3_15","DOI":"10.1007\/978-3-031-93448-3_15"},{"key":"21336_CR4","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-024-20451-0","author":"H Boulal","year":"2024","unstructured":"Boulal H, Hamidi M, Barkani J, Abarkan M (2024) Enhancing Amazigh ASR through convolutional neural networks and MFCC. Multimed Tools Appl. https:\/\/doi.org\/10.1007\/s11042-024-20451-0","journal-title":"Multimed Tools Appl"},{"key":"21336_CR5","doi-asserted-by":"publisher","unstructured":"Daouad M, Ataa Allah F, Dadi EW (2024) Enhancing automatic speech recognition systems for amazigh language through data augmentation. Lect Notes Networks Syst 887:866\u2013879. https:\/\/doi.org\/10.1007\/978-3-031-74491-4_67","DOI":"10.1007\/978-3-031-74491-4_67"},{"key":"21336_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 EW (2023) An automatic speech recognition system for isolated Amazigh word using 1D & 2D CNN-LSTM architecture. Int J Speech Technol 26:775\u2013787. https:\/\/doi.org\/10.1007\/s10772-023-10054-9","journal-title":"Int J Speech Technol"},{"key":"21336_CR7","doi-asserted-by":"publisher","unstructured":"Daouad M, Ataa Allah F, Dadi EW (2024) Amazigh speech recognition via parallel CNN Transformer-Encoder model. Lect Notes Inf Syst Organ 71 LNISO 255\u2013263. https:\/\/doi.org\/10.1007\/978-3-031-75329-9_28","DOI":"10.1007\/978-3-031-75329-9_28"},{"key":"21336_CR8","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"},{"key":"21336_CR9","unstructured":"Hao H, Zhou L, Liu S, Li J, Hu S, Wang R, Wei F (2023) Boosting Large Language Model for Speech Synthesis: An Empirical Study. 1\u201313"},{"key":"21336_CR10","unstructured":"Radford A, Kim JW, Xu T, Brockman G, McLeavey C, Sutskever I (2023) Robust speech recognition via large-scale weak supervision. Proc Mach Learn Res 202:28492\u201328518"},{"key":"21336_CR11","unstructured":"Baevski A, Zhou H, Mohamed A, Auli M (2020) wav2vec 2.0: A framework for self-supervised learning of speech representations. Adv Neural Inf Process Syst 2020-Decem, 1\u201312"},{"key":"21336_CR12","doi-asserted-by":"crossref","unstructured":"Liu Z, Kundu S, Li A, Wan J, Jiang L, Beerel PA (2024) AFLoRA: Adaptive Freezing of Low Rank Adaptation in Parameter Efficient Fine-Tuning of Large Models. arXiv Prepr. arXiv2403.13269","DOI":"10.18653\/v1\/2024.acl-short.16"},{"key":"21336_CR13","doi-asserted-by":"publisher","unstructured":"Feng T, Narayanan S (2023) PEFT-SER: On the Use of Parameter Efficient Transfer Learning Approaches For Speech Emotion Recognition Using Pre-trained Speech Models. 11th Int. Conf. Affect. Comput. Intell. Interact. ACII 2023. (2023). https:\/\/doi.org\/10.1109\/ACII59096.2023.10388152","DOI":"10.1109\/ACII59096.2023.10388152"},{"key":"21336_CR14","doi-asserted-by":"publisher","unstructured":"Mao Y, Ge Y, Fan Y, Xu W, Mi Y, Hu Z, Gao Y (2024) A survey on LoRA of large Language models. 0(1\u201331). https:\/\/doi.org\/10.1007\/s11704-024-40663-9","DOI":"10.1007\/s11704-024-40663-9"},{"key":"21336_CR15","unstructured":"Zhang Q, Chen M, Bukharin A, Karampatziakis N, He P, Cheng Y, Chen W, Zhao T (2023) AdaLoRA: adaptive budget allocation for Parameter-Efficient Fine-Tuning. 1\u201317"},{"key":"21336_CR16","doi-asserted-by":"publisher","unstructured":"Valipour M, Rezagholizadeh M, Kobyzev I, Ghodsi A (2023) DyLoRA: Parameter-Efficient tuning of pretrained models using dynamic Search-Free low rank adaptation. EACL 2023\u201317th Conf Eur Chapter Assoc Comput Linguist Proc Conf 3266\u20133279. https:\/\/doi.org\/10.18653\/v1\/2023.eacl-main.239","DOI":"10.18653\/v1\/2023.eacl-main.239"},{"key":"21336_CR17","doi-asserted-by":"publisher","unstructured":"Ding N, Lv X, Wang Q, Chen Y, Zhou B, Liu Z, Sun M (2023) Sparse Low-rank Adaptation of Pre-trained Language Models. EMNLP 2023\u20132023 Conf. Empir. Methods Nat. Lang. Process. Proc. 4133\u20134145 https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.252","DOI":"10.18653\/v1\/2023.emnlp-main.252"},{"key":"21336_CR18","doi-asserted-by":"publisher","unstructured":"Liu W, Qin Y, Peng Z, Lee T (2024) Sparsely shared Lora on whisper for child speech recognition. 11751\u201311755. https:\/\/doi.org\/10.1109\/icassp48485.2024.10447004","DOI":"10.1109\/icassp48485.2024.10447004"},{"key":"21336_CR19","doi-asserted-by":"crossref","unstructured":"Zhang R, Qiang R, Somayajula SA, Xie P (2024) AutoLoRA: Automatically Tuning Matrix Ranks in Low-Rank Adaptation Based on Meta Learning","DOI":"10.18653\/v1\/2024.naacl-long.282"},{"key":"21336_CR20","doi-asserted-by":"crossref","unstructured":"Meng F, Wang Z, Zhang M (2024) PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models. 1\u201323","DOI":"10.52202\/079017-3846"},{"key":"21336_CR21","unstructured":"Hayou S, Ghosh N, Yu B (2024) LoRA+: Efficient Low Rank Adaptation of Large Models. 3"},{"key":"21336_CR22","unstructured":"Liu S-Y, Wang C-Y, Yin H, Molchanov P, Wang Y-CF, Cheng K-T, Chen M-H (2024) DoRA: Weight-Decomposed Low-Rank Adaptation"},{"key":"21336_CR23","unstructured":"Qiang R, Zhang R, Xie P (2024) BiLoRA: A Bi-level Optimization Framework for Overfitting-Resilient Low-Rank Adaptation of Large Pre-trained Models"},{"key":"21336_CR24","unstructured":"Dettmers T, Pagnoni A, Holtzman A, Zettlemoyer L (2023) QLORA: efficient finetuning of quantized LLMs. Adv Neural Inf Process Syst 36"},{"key":"21336_CR25","unstructured":"Xu Y, Xie L, Gu X, Chen X, Chang H, Zhang H, Chen Z, Zhang X, Tian Q (2023) QA-LoRA: Quantization-Aware Low-Rank adaptation of large Language models. 1\u201316"},{"key":"21336_CR26","doi-asserted-by":"crossref","unstructured":"Rajabzadeh H, Valipour M, Zhu T, Tahaei M, Kwon HJ, Ghodsi A, Chen B, Rezagholizadeh M (2024) QDyLoRA: Quantized Dynamic Low-Rank Adaptation for Efficient Large Language Model Tuning","DOI":"10.18653\/v1\/2024.emnlp-industry.53"},{"key":"21336_CR27","unstructured":"Yu Y, Yang C-HH, Dinh T, Ryu S, Kolehmainen J, Ren R, Filimonov D, Shivakumar PG, Gandhe A, Rastow A, Xu J, Bulyko I, Stolcke A (2024) Investigating Training Strategies and Model Robustness of Low-Rank Adaptation for Language Modeling in Speech Recognition. 2\u20136"},{"key":"21336_CR28","doi-asserted-by":"crossref","unstructured":"Khassanov Y, Chen Z, Chen T, Chong TY, Li W, Zhang J, Lu L, Wang Y (2024) Dual-Pipeline with Low-Rank Adaptation for New Language Integration in Multilingual ASR","DOI":"10.21437\/Interspeech.2024-348"},{"key":"21336_CR29","doi-asserted-by":"crossref","unstructured":"Palaskar S, Rudovic O, Dharur S, Pesce F, Krishna G, Sivaraman A, Berkowitz J, Abdelaziz AH, Adya S, Tewfik A (2024) Multimodal Large Language Models with Fusion Low Rank Adaptation for Device Directed Speech Detection","DOI":"10.21437\/Interspeech.2024-1361"},{"key":"21336_CR30","doi-asserted-by":"crossref","unstructured":"Jairam R, Jyothish Lal G, Premjith B (2024) A Few-Shot Multi-Accented Speech Classification for Indian Languages using Transformers and LLM\u2019s Fine-Tuning Approaches. DravidianLangTech 2024\u20134th Work. Speech, Vision, Lang. Technol. Dravidian Lang. Proc. Work. 1\u20139","DOI":"10.18653\/v1\/2024.dravidianlangtech-1.1"},{"key":"21336_CR31","doi-asserted-by":"publisher","unstructured":"Fine-tuning L (2024) Enhancing whisper model for Vietnamese specific domain with data enhancing whisper model performance for Vietnamese specific domain with data blending and LoRA Fine- tuning. https:\/\/doi.org\/10.1007\/978-981-97-5504-2","DOI":"10.1007\/978-981-97-5504-2"},{"key":"21336_CR32","doi-asserted-by":"crossref","unstructured":"Jiang Y, Wang T, Xie X, Liu J, Sun W, Yan N, Chen H, Wang L, Liu X, Tian F (2024) Perceiver-Prompt: Flexible Speaker Adaptation in Whisper for Chinese Disordered Speech Recognition","DOI":"10.21437\/Interspeech.2024-852"},{"key":"21336_CR33","doi-asserted-by":"crossref","unstructured":"Xu T, Huang K, Guo P, Zhou Y, Huang L, Xue H, Xie L (2024) Towards Rehearsal-Free Multilingual ASR: A LoRA-based Case Study on Whisper","DOI":"10.21437\/Interspeech.2024-1953"},{"key":"21336_CR34","unstructured":"Zhang Y, Han W, Qin J, Wang Y, Bapna A, Chen Z, Chen N, Li B, Axelrod V, Wang G, Meng Z, Hu K, Rosenberg A, Prabhavalkar R, Park DS, Haghani P, Riesa J, Perng G, Soltau H, Strohman T, Ramabhadran B, Sainath T, Moreno P, Chiu C-C, Schalkwyk J, Beaufays F, Wu Y (2023) Google USM: scaling automatic speech recognition beyond 100 languages"},{"key":"21336_CR35","unstructured":"Le T-T, Nguyen LT, Nguyen DQ (2024) PhoWhisper: Automatic Speech Recognition for Vietnamese"},{"key":"21336_CR36","unstructured":"Ding S, Guo A, Nguyen A, Wang J, Zhou M (2022) Robust automatic speech recognition and transcription With Wav2Vec 2. 0 and Whisper. Data Sci. Capstone Proj. With accent. AI"},{"key":"21336_CR37","unstructured":"Hu E, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, Wang L, Chen W (2022) Lora: Low-Rank adaptation of large Language Models. ICLR 2022\u201310th int. Conf Learn Represent 1\u201326"},{"key":"21336_CR38","doi-asserted-by":"publisher","first-page":"1937","DOI":"10.1007\/s11063-018-09977-1","volume":"50","author":"YS Aurelio","year":"2019","unstructured":"Aurelio YS, de Almeida GM, de Castro CL, Braga AP (2019) Learning from imbalanced data sets with weighted cross-entropy function. Neural Process Lett 50:1937\u20131949. https:\/\/doi.org\/10.1007\/s11063-018-09977-1","journal-title":"Neural Process Lett"},{"key":"21336_CR39","unstructured":"Grandini M, Bagli E, Visani G (2020) Metrics for Multi-Class Classification: an Overview. 1\u201317"},{"key":"21336_CR40","doi-asserted-by":"publisher","unstructured":"Yacouby R, Axman D (2020) Probabilistic extension of Precision, Recall, and F1 score for more thorough evaluation of classification models. 79\u201391. https:\/\/doi.org\/10.18653\/v1\/2020.eval4nlp-1.9","DOI":"10.18653\/v1\/2020.eval4nlp-1.9"},{"key":"21336_CR41","doi-asserted-by":"crossref","unstructured":"Liao X, Wang C, Zhou S, Hu J, Zheng H, Gao J (2025) Dynamic Adaptation of LoRA Fine-Tuning for Efficient and Task-Specific Optimization of Large Language Models","DOI":"10.1145\/3730436.3730456"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-026-21336-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-026-21336-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-026-21336-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T22:33:14Z","timestamp":1772058794000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-026-21336-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,25]]},"references-count":41,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["21336"],"URL":"https:\/\/doi.org\/10.1007\/s11042-026-21336-0","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,25]]},"assertion":[{"value":"24 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 August 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 September 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 February 2026","order":4,"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":"Competing interests"}}],"article-number":"189"}}