{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T21:57:05Z","timestamp":1781301425512,"version":"3.54.1"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62101163"],"award-info":[{"award-number":["62101163"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013076","name":"National Major Science and Technology Projects of China","doi-asserted-by":"publisher","award":["2025ZD0123702"],"award-info":[{"award-number":["2025ZD0123702"]}],"id":[{"id":"10.13039\/501100013076","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005046","name":"Heilongjiang Province Natural Science Foundation","doi-asserted-by":"publisher","award":["YQ2024F018"],"award-info":[{"award-number":["YQ2024F018"]}],"id":[{"id":"10.13039\/501100005046","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113706","type":"journal-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T17:17:23Z","timestamp":1776100643000},"page":"113706","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["Fine-tuned Whisper-based semantic-temporal aggregation networks for sound event classification"],"prefix":"10.1016","volume":"179","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1957-6432","authenticated-orcid":false,"given":"Chen","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fengwei","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2736-829X","authenticated-orcid":false,"given":"Liang","family":"Xi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113706_b1","doi-asserted-by":"crossref","first-page":"2297","DOI":"10.1109\/TASLP.2024.3385287","article-title":"Few-shot class-incremental audio classification with adaptive mitigation of forgetting and overfitting","volume":"32","author":"Li","year":"2024","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.patcog.2026.113706_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111432","article-title":"Audio-visual representation learning via knowledge distillation from speech foundation models","volume":"162","author":"Zhang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113706_b3","doi-asserted-by":"crossref","first-page":"3947","DOI":"10.1109\/TASLP.2024.3451983","article-title":"Sound activity-aware based cross-task collaborative training for semi-supervised sound event detection","volume":"32","author":"Guan","year":"2024","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.patcog.2026.113706_b4","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"911","article-title":"Fine-tune the pretrained ATST model for sound event detection","author":"Shao","year":"2024"},{"key":"10.1016\/j.patcog.2026.113706_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110200","article-title":"IIOF: Intra-and inter-feature orthogonal fusion of local and global features for music emotion recognition","volume":"148","author":"Chang","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113706_b6","article-title":"A systematic review of interpretability and explainability for speech emotion features in automatic speech emotion recognition","author":"Jayasinghe","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113706_b7","doi-asserted-by":"crossref","first-page":"570","DOI":"10.1109\/TASLPRO.2025.3527143","article-title":"Learnable counterfactual attention for music classification","volume":"33","author":"Lin","year":"2025","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.patcog.2026.113706_b8","series-title":"European Signal Processing Conference","first-page":"411","article-title":"Pre-training music classification models via music source separation","author":"Garoufis","year":"2024"},{"key":"10.1016\/j.patcog.2026.113706_b9","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"321","article-title":"An ontology-aware framework for audio event classification","author":"Sun","year":"2020"},{"key":"10.1016\/j.patcog.2026.113706_b10","series-title":"Conference of the International Speech Communication Association","first-page":"571","article-title":"AST: Audio spectrogram transformer","author":"Gong","year":"2021"},{"key":"10.1016\/j.patcog.2026.113706_b11","series-title":"Conference of the International Speech Communication Association","first-page":"2753","article-title":"Efficient training of audio transformers with patchout","author":"Koutini","year":"2021"},{"key":"10.1016\/j.patcog.2026.113706_b12","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"646","article-title":"HTS-AT: A hierarchical token-semantic audio transformer for sound classification and detection","author":"Chen","year":"2022"},{"key":"10.1016\/j.patcog.2026.113706_b13","series-title":"International Conference on Machine Learning","first-page":"5178","article-title":"BEATs: Audio pre-training with acoustic tokenizers","author":"Chen","year":"2023"},{"key":"10.1016\/j.patcog.2026.113706_b14","unstructured":"W. Chen, Y. Liang, Z. Ma, Z. Zheng, X. Chen, EAT: Self-supervised pre-training with efficient audio transformer, in: International Joint Conference on Artificial Intelligence, 2024, pp. 3807\u20133815."},{"key":"10.1016\/j.patcog.2026.113706_b15","series-title":"International Conference on Machine Learning","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023"},{"key":"10.1016\/j.patcog.2026.113706_b16","series-title":"Conference of the International Speech Communication Association","first-page":"2798","article-title":"Whisper-AT: Noise-robust automatic speech recognizers are also strong general audio event taggers","author":"Gong","year":"2023"},{"key":"10.1016\/j.patcog.2026.113706_b17","series-title":"Speaker and language change detection using wav2vec2 and whisper","author":"Berns","year":"2023"},{"key":"10.1016\/j.patcog.2026.113706_b18","series-title":"Conference of the International Speech Communication Association","first-page":"4134","article-title":"Classification of vocal intensity category from speech using the wav2vec2 and whisper embeddings","author":"Kodali","year":"2023"},{"key":"10.1016\/j.patcog.2026.113706_b19","series-title":"International Conference on Pattern Recognition and Machine Intelligence","first-page":"708","article-title":"Noise robust whisper features for dysarthric severity-level classification","author":"Rathod","year":"2023"},{"key":"10.1016\/j.patcog.2026.113706_b20","doi-asserted-by":"crossref","unstructured":"A. Gulli, F. Costantini, D. Sidraschi, E.L. Destri, Fine-Tuning a Pre-Trained Wav2Vec2 Model for Automatic Speech Recognition-Experiments with De Zahrar Sproche, in: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), 2024, pp. 7336\u20137342.","DOI":"10.63317\/268tgik2ufyk"},{"issue":"6","key":"10.1016\/j.patcog.2026.113706_b21","doi-asserted-by":"crossref","first-page":"1291","DOI":"10.1109\/TASLP.2017.2690575","article-title":"Convolutional recurrent neural networks for polyphonic sound event detection","volume":"25","author":"Cak\u0131r","year":"2017","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.patcog.2026.113706_b22","doi-asserted-by":"crossref","first-page":"2880","DOI":"10.1109\/TASLP.2020.3030497","article-title":"PANNS: Large-scale pretrained audio neural networks for audio pattern recognition","volume":"28","author":"Kong","year":"2020","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.patcog.2026.113706_b23","doi-asserted-by":"crossref","first-page":"3292","DOI":"10.1109\/TASLP.2021.3120633","article-title":"PSLA: Improving audio tagging with pretraining, sampling, labeling, and aggregation","volume":"29","author":"Gong","year":"2021","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.patcog.2026.113706_b24","first-page":"10699","article-title":"SSAST: Self-supervised audio spectrogram transformer","volume":"vol. 36","author":"Gong","year":"2022"},{"key":"10.1016\/j.patcog.2026.113706_b25","series-title":"Conference of the International Speech Communication Association","first-page":"2438","article-title":"MAE-AST: Masked autoencoding audio spectrogram transformer","author":"Baade","year":"2022"},{"key":"10.1016\/j.patcog.2026.113706_b26","first-page":"28708","article-title":"Masked autoencoders that listen","volume":"35","author":"Huang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113706_b27","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"13421","article-title":"Can whisper perform speech-based in-context learning?","author":"Wang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113706_b28","series-title":"IEEE International Conference on Multimedia and Expo","first-page":"1","article-title":"A study on incorporating whisper for robust speech assessment","author":"Zezario","year":"2024"},{"key":"10.1016\/j.patcog.2026.113706_b29","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113706_b30","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"7505","article-title":"Positive transfer of the whisper speech transformer to human and animal voice activity detection","author":"Gu","year":"2024"},{"issue":"13","key":"10.1016\/j.patcog.2026.113706_b31","doi-asserted-by":"crossref","first-page":"10337","DOI":"10.1007\/s00521-022-06896-0","article-title":"Combined angular margin and cosine margin softmax loss for music classification based on spectrograms","volume":"34","author":"Li","year":"2022","journal-title":"Neural Comput. Appl."},{"issue":"5","key":"10.1016\/j.patcog.2026.113706_b32","doi-asserted-by":"crossref","DOI":"10.1111\/exsy.12804","article-title":"Environmental sound classification using convolution neural networks with different integrated loss functions","volume":"39","author":"Das","year":"2022","journal-title":"Expert Syst."},{"key":"10.1016\/j.patcog.2026.113706_b33","first-page":"28708","article-title":"Masked autoencoders that listen","volume":"35","author":"Huang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113706_b34","series-title":"International Joint Conference on Neural Networks","first-page":"1","article-title":"Deep feature embedding and hierarchical classification for audio scene classification","author":"Pham","year":"2020"},{"key":"10.1016\/j.patcog.2026.113706_b35","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"6","article-title":"Hierarchy-aware loss function on a tree structured label space for audio event detection","author":"Jati","year":"2019"},{"key":"10.1016\/j.patcog.2026.113706_b36","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"3623","article-title":"Rank-based loss for learning hierarchical representations","author":"Nolasco","year":"2022"},{"key":"10.1016\/j.patcog.2026.113706_b37","doi-asserted-by":"crossref","unstructured":"J. Hu, L. Shen, G. Sun, Squeeze-and-excitation networks, in: IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7132\u20137141.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"10.1016\/j.patcog.2026.113706_b38","doi-asserted-by":"crossref","unstructured":"K.J. Piczak, ESC: Dataset for environmental sound classification, in: ACM International Conference on Multimedia, 2015, pp. 1015\u20131018.","DOI":"10.1145\/2733373.2806390"},{"key":"10.1016\/j.patcog.2026.113706_b39","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"776","article-title":"Audio set: An ontology and human-labeled dataset for audio events","author":"Gemmeke","year":"2017"},{"key":"10.1016\/j.patcog.2026.113706_b40","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.2026.113706_b41","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1109\/TASLP.2021.3133208","article-title":"Fsd50k: an open dataset of human-labeled sound events","volume":"30","author":"Fonseca","year":"2021","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.patcog.2026.113706_b42","series-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"10.1016\/j.patcog.2026.113706_b43","unstructured":"S. Yadav, S. Theodoridis, L.K. Hansen, Z.-H. Tan, Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners, in: The Twelfth International Conference on Learning Representations, 2024."},{"issue":"28","key":"10.1016\/j.patcog.2026.113706_b44","doi-asserted-by":"crossref","first-page":"71359","DOI":"10.1007\/s11042-024-18421-7","article-title":"Multiclass environmental sound classification model based on adding residual connections to self-attention layers","volume":"83","author":"Nasef","year":"2024","journal-title":"Multimedia Tools Appl."},{"key":"10.1016\/j.patcog.2026.113706_b45","series-title":"2024 IEEE Spoken Language Technology Workshop","first-page":"1053","article-title":"SSAMBA: Self-supervised audio representation learning with mamba state space model","author":"Shams","year":"2024"},{"key":"10.1016\/j.patcog.2026.113706_b46","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"Masked spectrogram prediction for self-supervised audio pre-training","author":"Chong","year":"2023"},{"key":"10.1016\/j.patcog.2026.113706_b47","series-title":"International Conference on Machine Learning","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","author":"Baevski","year":"2022"},{"key":"10.1016\/j.patcog.2026.113706_b48","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"Cat: Causal audio transformer for audio classification","author":"Liu","year":"2023"},{"key":"10.1016\/j.patcog.2026.113706_b49","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"976","article-title":"Audioclip: Extending clip to image, text and audio","author":"Guzhov","year":"2022"},{"issue":"22","key":"10.1016\/j.patcog.2026.113706_b50","doi-asserted-by":"crossref","first-page":"8874","DOI":"10.3390\/s22228874","article-title":"Transformers for urban sound classification\u2014A comprehensive performance evaluation","volume":"22","author":"Nogueira","year":"2022","journal-title":"Sensors"},{"key":"10.1016\/j.patcog.2026.113706_b51","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"Clap learning audio concepts from natural language supervision","author":"Elizalde","year":"2023"},{"key":"10.1016\/j.patcog.2026.113706_b52","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"Lhgnn: Local-higher order graph neural networks for audio classification and tagging","author":"Singh","year":"2025"},{"key":"10.1016\/j.patcog.2026.113706_b53","article-title":"Cmkd: Cnn\/transformer-based cross-model knowledge distillation for audio classification","author":"Gong","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113706_b54","series-title":"Conference of the International Speech Communication Association","first-page":"721","article-title":"Robust wav2vec 2.0: Analyzing domain shift in self-supervised pre-training","author":"Hsu","year":"2021"},{"key":"10.1016\/j.patcog.2026.113706_b55","doi-asserted-by":"crossref","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","article-title":"Hubert: Self-supervised speech representation learning by masked prediction of hidden units","volume":"29","author":"Hsu","year":"2021","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326006710?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326006710?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T21:18:21Z","timestamp":1781299101000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326006710"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":55,"alternative-id":["S0031320326006710"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113706","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Fine-tuned Whisper-based semantic-temporal aggregation networks for sound event classification","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113706","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113706"}}