{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T11:52:56Z","timestamp":1781869976454,"version":"3.54.5"},"reference-count":35,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T00:00:00Z","timestamp":1781827200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114250","type":"journal-article","created":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T18:42:22Z","timestamp":1781462542000},"page":"114250","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["FedMLAC: Mutual learning driven heterogeneous federated audio classification"],"prefix":"10.1016","volume":"180","author":[{"given":"Jun","family":"Bai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rajib","family":"Rana","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4753-8161","authenticated-orcid":false,"given":"Di","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youyang","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohui","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carlos","family":"Busso","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shivakumara","family":"Palaiahnakote","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114250_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111143","article-title":"FedKT: Federated learning with knowledge transfer for non-IID data","volume":"159","author":"Mao","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114250_b2","series-title":"2022 International Joint Conference on Neural Networks","first-page":"1","article-title":"Fedewa: Federated learning with elastic weighted averaging","author":"Bai","year":"2022"},{"key":"10.1016\/j.patcog.2026.114250_b3","series-title":"Proceedings of the 3rd Workshop on Machine Learning and Systems","first-page":"64","article-title":"Distributed training for speech recognition using local knowledge aggregation and knowledge distillation in heterogeneous systems","author":"Shi","year":"2023"},{"key":"10.1016\/j.patcog.2026.114250_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109635","article-title":"Robust federated learning under statistical heterogeneity via Hessian spectral decomposition","volume":"141","author":"Ahmad","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114250_b5","doi-asserted-by":"crossref","unstructured":"J. Bai, Y. Song, D. Wu, A. Sajjanhar, Y. Xiang, W. Zhou, X. Tao, Y. Li, Y. Li, A unified solution to diverse heterogeneities in one-shot federated learning, in: Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2, 2025, pp. 71\u201382.","DOI":"10.1145\/3711896.3736825"},{"key":"10.1016\/j.patcog.2026.114250_b6","unstructured":"D. Wu, J. Bai, Y. Song, J. Chen, W. Zhou, Y. Xiang, A. Sajjanhar, FedInverse: Evaluating privacy leakage in federated learning, in: The Twelfth International Conference on Learning Representations, 2024."},{"key":"10.1016\/j.patcog.2026.114250_b7","series-title":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops","first-page":"1","article-title":"Federated semi-supervised learning for industrial sound analysis and keyword spotting","author":"Grollmisch","year":"2025"},{"key":"10.1016\/j.patcog.2026.114250_b8","doi-asserted-by":"crossref","DOI":"10.1109\/TCE.2025.3542791","article-title":"Non-IID free federated learning with fuzzy optimization for consumer electronics systems","author":"Bai","year":"2025","journal-title":"IEEE Trans. Consum. Electron."},{"key":"10.1016\/j.patcog.2026.114250_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.110396","article-title":"SASE: Self-adaptive noise distribution network for speech enhancement with federated learning using heterogeneous data","volume":"266","author":"Lin","year":"2023","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.patcog.2026.114250_b10","first-page":"270","article-title":"Distributed speech recognition with heterogeneous data","volume":"29","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.patcog.2026.114250_b11","article-title":"Fedtp: Federated learning by transformer personalization","author":"Li","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2026.114250_b12","series-title":"Parameter-efficient transfer learning under federated learning for automatic speech recognition","author":"Kan","year":"2024"},{"key":"10.1016\/j.patcog.2026.114250_b13","article-title":"Federated incremental named entity recognition","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.patcog.2026.114250_b14","series-title":"2025 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"EFL-PEFT: A communication Efficient Federated Learning framework using PEFT sparsification for ASR","author":"Ali","year":"2025"},{"issue":"2","key":"10.1016\/j.patcog.2026.114250_b15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3626242","article-title":"Labeling chaos to learning harmony: Federated learning with noisy labels","volume":"15","author":"Tsouvalas","year":"2024","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"10.1016\/j.patcog.2026.114250_b16","article-title":"Unsupervised speaker diarization in distributed IoT networks using federated learning","author":"Bhuyan","year":"2024","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"10.1016\/j.patcog.2026.114250_b17","doi-asserted-by":"crossref","unstructured":"W.-T. Hsu, C.-P. Chen, Y.-S. Lin, C.-C. Lee, A Cluster-based Personalized Federated Learning Strategy for End-to-End ASR of Dementia Patients, in: Proceedings of Interspeech 2024, 2024, pp. 2450\u20132454.","DOI":"10.21437\/Interspeech.2024-470"},{"issue":"7","key":"10.1016\/j.patcog.2026.114250_b18","doi-asserted-by":"crossref","first-page":"1485","DOI":"10.3390\/electronics14071485","article-title":"Dynamic client selection and group-balanced personalization for data-imbalanced federated speech recognition","volume":"14","author":"Xu","year":"2025","journal-title":"Electronics"},{"key":"10.1016\/j.patcog.2026.114250_b19","series-title":"2024 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"10001","article-title":"Communication-efficient personalized federated learning for speech-to-text tasks","author":"Du","year":"2024"},{"key":"10.1016\/j.patcog.2026.114250_b20","series-title":"2021 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"3015","article-title":"Federated learning with heterogeneous clients: A study on speech recognition","author":"Amiri","year":"2021"},{"key":"10.1016\/j.patcog.2026.114250_b21","doi-asserted-by":"crossref","unstructured":"H. Zhu, J. Wang, G. Cheng, P. Zhang, Y. Yan, Decoupled Federated Learning for ASR with Non-IID Data, in: Proceedings of Interspeech 2022, 2022, pp. 2628\u20132632.","DOI":"10.21437\/Interspeech.2022-720"},{"key":"10.1016\/j.patcog.2026.114250_b22","series-title":"2022 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"481","article-title":"Federated self-supervised learning for acoustic event classification","author":"Feng","year":"2022"},{"key":"10.1016\/j.patcog.2026.114250_b23","series-title":"2022 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"476","article-title":"Federated self-training for data-efficient audio recognition","author":"Tsouvalas","year":"2022"},{"key":"10.1016\/j.patcog.2026.114250_b24","series-title":"Proceedings of Interspeech 2022","first-page":"536","article-title":"Federated domain adaptation for ASR with full self-supervision","author":"Jia","year":"2022"},{"key":"10.1016\/j.patcog.2026.114250_b25","series-title":"Artificial Intelligence and Statistics","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017"},{"key":"10.1016\/j.patcog.2026.114250_b26","doi-asserted-by":"crossref","unstructured":"Y. Zhang, T. Xiang, T.M. Hospedales, H. Lu, Deep mutual learning, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 4320\u20134328.","DOI":"10.1109\/CVPR.2018.00454"},{"key":"10.1016\/j.patcog.2026.114250_b27","doi-asserted-by":"crossref","unstructured":"J. Lu, S. Li, K. Bao, P. Wang, Z. Qian, S. Ge, Federated learning with label-masking distillation, in: Proceedings of the 31st ACM International Conference on Multimedia, 2023, pp. 222\u2013232.","DOI":"10.1145\/3581783.3611984"},{"key":"10.1016\/j.patcog.2026.114250_b28","article-title":"Federated optimization in heterogeneous networks","author":"Li","year":"2020","journal-title":"IEEE Trans. Signal Process."},{"key":"10.1016\/j.patcog.2026.114250_b29","series-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018"},{"key":"10.1016\/j.patcog.2026.114250_b30","doi-asserted-by":"crossref","unstructured":"J. Salamon, C. Jacoby, J.P. Bello, A dataset and taxonomy for urban sound research, in: Proceedings of the 22nd ACM International Conference on Multimedia, 2014, pp. 1041\u20131044.","DOI":"10.1145\/2647868.2655045"},{"key":"10.1016\/j.patcog.2026.114250_b31","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","article-title":"IEMOCAP: Interactive emotional dyadic motion capture database","volume":"42","author":"Busso","year":"2008","journal-title":"Lang. Resour. Eval."},{"issue":"4","key":"10.1016\/j.patcog.2026.114250_b32","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1109\/TAFFC.2014.2336244","article-title":"Crema-d: Crowd-sourced emotional multimodal actors dataset","volume":"5","author":"Cao","year":"2014","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.patcog.2026.114250_b33","series-title":"2023 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"Fedaudio: A federated learning benchmark for audio tasks","author":"Zhang","year":"2023"},{"key":"10.1016\/j.patcog.2026.114250_b34","series-title":"International Conference on Learning Representations","article-title":"Adaptive federated optimization","author":"Reddi","year":"2021"},{"key":"10.1016\/j.patcog.2026.114250_b35","series-title":"Musan: A music, speech, and noise corpus","author":"Snyder","year":"2015"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S003132032601215X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S003132032601215X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T11:21:48Z","timestamp":1781868108000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S003132032601215X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":35,"alternative-id":["S003132032601215X"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114250","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"FedMLAC: Mutual learning driven heterogeneous federated audio classification","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114250","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"114250"}}