{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T20:26:56Z","timestamp":1783024016433,"version":"3.54.6"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"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":["62173232"],"award-info":[{"award-number":["62173232"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62003214"],"award-info":[{"award-number":["62003214"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62303324"],"award-info":[{"award-number":["62303324"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Biomedical Signal Processing and Control"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.bspc.2026.110753","type":"journal-article","created":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T00:11:55Z","timestamp":1781050315000},"page":"110753","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["MSTFF-Net: Multi-scale spatio-temporal\u2013frequency feature fusion for auditory attention detection"],"prefix":"10.1016","volume":"125","author":[{"given":"Yangzhi","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1733-4763","authenticated-orcid":false,"given":"Chaoli","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhanquan","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.bspc.2026.110753_b1","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1121\/1.1907229","article-title":"Some experiments on the recognition of speech, with one and with two ears","volume":"25","author":"Cherry","year":"1953","journal-title":"J. Acoust. Soc. Am."},{"issue":"1","key":"10.1016\/j.bspc.2026.110753_b2","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1152\/jn.00297.2011","article-title":"Neural coding of continuous speech in auditory cortex during monaural and dichotic listening","volume":"107","author":"Ding","year":"2012","journal-title":"J. Neurophysiol."},{"issue":"1","key":"10.1016\/j.bspc.2026.110753_b3","doi-asserted-by":"crossref","first-page":"11538","DOI":"10.1038\/s41598-019-47795-0","article-title":"Comparison of two-talker attention decoding from EEG with nonlinear neural networks and linear methods","volume":"9","author":"Ciccarelli","year":"2019","journal-title":"Sci. Rep."},{"issue":"12","key":"10.1016\/j.bspc.2026.110753_b4","doi-asserted-by":"crossref","first-page":"4030","DOI":"10.3390\/jcm12124030","article-title":"Factors impacting the use or rejection of hearing aids\u2014A systematic review and meta-analysis","volume":"12","author":"Marcos-Alonso","year":"2023","journal-title":"J. Clin. Med."},{"issue":"7397","key":"10.1016\/j.bspc.2026.110753_b5","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1038\/nature11020","article-title":"Selective cortical representation of attended speaker in multi-talker speech perception","volume":"485","author":"Mesgarani","year":"2012","journal-title":"Nature"},{"key":"10.1016\/j.bspc.2026.110753_b6","doi-asserted-by":"crossref","first-page":"700655","DOI":"10.3389\/fphys.2021.700655","article-title":"Extracting the auditory attention in a dual-speaker scenario from EEG using a joint CNN-LSTM model","volume":"12","author":"Kuruvila","year":"2021","journal-title":"Front. Physiol."},{"key":"10.1016\/j.bspc.2026.110753_b7","doi-asserted-by":"crossref","unstructured":"Hannah L. Stone, et al., Anatomically distinct regions in the inferior frontal cortex are modulated by task and reading skill, J. Neurosci. 45 (19) 2025.","DOI":"10.1523\/JNEUROSCI.1767-24.2025"},{"key":"10.1016\/j.bspc.2026.110753_b8","doi-asserted-by":"crossref","first-page":"110713","DOI":"10.1016\/j.brainresbull.2023.110713","article-title":"Artificial intelligence based multimodal language decoding from brain activity: a review","volume":"201","author":"Zhao","year":"2023","journal-title":"Brain Research Bulletin"},{"issue":"4","key":"10.1016\/j.bspc.2026.110753_b9","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1109\/MSP.2021.3075932","article-title":"Electroencephalography-based auditory attention decoding: Toward neurosteered hearing devices","volume":"38","author":"Geirnaert","year":"2021","journal-title":"IEEE Signal Process. Mag."},{"issue":"4","key":"10.1016\/j.bspc.2026.110753_b10","doi-asserted-by":"crossref","first-page":"041003","DOI":"10.1088\/1741-2552\/ace73f","article-title":"Relating EEG to continuous speech using deep neural networks: a review","volume":"20","author":"Puffay","year":"2023","journal-title":"J. Neural Eng."},{"key":"10.1016\/j.bspc.2026.110753_b11","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.56481","article-title":"EEG-based detection of the locus of auditory attention with convolutional neural networks","volume":"10","author":"Vandecappelle","year":"2021","journal-title":"Elife"},{"key":"10.1016\/j.bspc.2026.110753_b12","series-title":"ICASSP 2020-2020 IEEE Interna- tional Conference on Acoustics, Speech and Signal Processing","article-title":"An LSTM based architecture to relate speech stimulus to EEG","author":"Monesi","year":"2020"},{"issue":"7","key":"10.1016\/j.bspc.2026.110753_b13","doi-asserted-by":"crossref","first-page":"2233","DOI":"10.1109\/TBME.2022.3140246","article-title":"STAnet: A spatiotemporal attention network for decoding auditory spatial attention from EEG","volume":"69","author":"Su","year":"2022","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"10.1016\/j.bspc.2026.110753_b14","unstructured":"Qinke Ni, et al., DBPNet: Dual-Branch Parallel Network with Temporal-Frequency Fusion for Auditory Attention Detection, in: Proceedings of the International Joint Conference on Artificial Intelligence, IJCAI, 2024."},{"key":"10.1016\/j.bspc.2026.110753_b15","doi-asserted-by":"crossref","first-page":"102946","DOI":"10.1016\/j.inffus.2025.102946","article-title":"Seeing helps hearing: A multi-modal dataset and a mamba-based dual branch parallel network for auditory attention decoding","volume":"118","author":"Fan","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.bspc.2026.110753_b16","doi-asserted-by":"crossref","first-page":"31688","DOI":"10.52202\/079017-0995","article-title":"Darnet: Dual attention refinement network with spatiotemporal construction for auditory attention detection","volume":"37","author":"Yan","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.bspc.2026.110753_b17","series-title":"MHANet: Multi-scale Hybrid Attention Network for Auditory Attention Detection","author":"Li","year":"2025"},{"key":"10.1016\/j.bspc.2026.110753_b18","series-title":"ListenNet: A Lightweight Spatio-Temporal Enhancement Nested Network for Auditory Attention Detection","author":"Fan","year":"2025"},{"key":"10.1016\/j.bspc.2026.110753_b19","unstructured":"S2M-Former: Spiking Symmetric Mixing Branchformer for Brain Auditory Attention Detection."},{"issue":"1","key":"10.1016\/j.bspc.2026.110753_b20","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1109\/TAFFC.2025.3611173","article-title":"STRFLNet: Spatio-temporal representation fusion learning network for EEG-based emotion recognition","volume":"17","author":"Hu","year":"2026","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.bspc.2026.110753_b21","doi-asserted-by":"crossref","first-page":"104835","DOI":"10.1016\/j.bspc.2023.104835","article-title":"EEG emotion recognition using attention-based convolutional transformer neural network","volume":"84","author":"Gong","year":"2023","journal-title":"Biomed. Signal Process. Control."},{"issue":"5","key":"10.1016\/j.bspc.2026.110753_b22","doi-asserted-by":"crossref","first-page":"1557","DOI":"10.1109\/TBME.2020.3033446","article-title":"Fast EEG-based decoding of the directional focus of auditory attention using common spatial patterns","volume":"68","author":"Geirnaert","year":"2020","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"10.1016\/j.bspc.2026.110753_b23","series-title":"ICASSP 2021-2021 IEEE International Conference on Acous- tics, Speech and Signal Processing","article-title":"Riemannian geometry-based decoding of the directional focus of auditory attention using eeg","author":"Geirnaert","year":"2021"},{"key":"10.1016\/j.bspc.2026.110753_b24","doi-asserted-by":"crossref","first-page":"110129","DOI":"10.1016\/j.compbiomed.2025.110129","article-title":"Atten-Nonlocal Unet: Attention and Non-local Unet for medical image segmentation","volume":"191","author":"Jia","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.bspc.2026.110753_b25","doi-asserted-by":"crossref","unstructured":"Jie Hu, Li Shen, Gang Sun, Squeeze-and-excitation networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"10.1016\/j.bspc.2026.110753_b26","series-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018"},{"issue":"3","key":"10.1016\/j.bspc.2026.110753_b27","doi-asserted-by":"crossref","DOI":"10.1088\/1741-2552\/ad4f1a","article-title":"Attention-guided graph structure learning network for EEG-enabled auditory attention detection","volume":"21","author":"Zeng","year":"2024","journal-title":"J. Neural Eng."},{"issue":"11","key":"10.1016\/j.bspc.2026.110753_b28","doi-asserted-by":"crossref","first-page":"5391","DOI":"10.1002\/hbm.23730","article-title":"Deep learning with convolutional neural networks for EEG decoding and visualization","volume":"38","author":"Schirrmeister","year":"2017","journal-title":"Hum. Brain Mapp."},{"key":"10.1016\/j.bspc.2026.110753_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2024.108302","article-title":"Pfd-net: Pyramid fourier deformable network for medical image segmentation","volume":"172","author":"Yang","year":"2024","journal-title":"Comput. Biol. Med."},{"issue":"5","key":"10.1016\/j.bspc.2026.110753_b30","doi-asserted-by":"crossref","DOI":"10.1088\/1741-2552\/ac975c","article-title":"Detecting the locus of auditory attention based on the spectro-spatial\u2013temporal analysis of EEG","volume":"19","author":"Jiang","year":"2022","journal-title":"J. Neural Eng."},{"key":"10.1016\/j.bspc.2026.110753_b31","series-title":"2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society","article-title":"Low-latency auditory spatial attention detection based on spectro-spatial features from eeg","author":"Cai","year":"2021"},{"key":"10.1016\/j.bspc.2026.110753_b32","unstructured":"Yimian Dai, et al., Attentional feature fusion, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2021."},{"key":"10.1016\/j.bspc.2026.110753_b33","series-title":"Auditory attention detection dataset kuleuven","author":"Das","year":"2019"},{"issue":"5","key":"10.1016\/j.bspc.2026.110753_b34","doi-asserted-by":"crossref","first-page":"056014","DOI":"10.1088\/1741-2560\/13\/5\/056014","article-title":"The effect of head-related filtering and ear-specific decoding bias on auditory attention detection","volume":"13","author":"Das","year":"2016","journal-title":"J. Neural Eng."},{"key":"10.1016\/j.bspc.2026.110753_b35","series-title":"Eeg and audio dataset for auditory attention decoding","author":"Fuglsang","year":"2018"},{"key":"10.1016\/j.bspc.2026.110753_b36","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1016\/j.neuroimage.2017.04.026","article-title":"Noise-robust cortical tracking of attended speech in real-world acoustic scenes","volume":"156","author":"Fuglsang","year":"2017","journal-title":"NeuroImage"},{"key":"10.1016\/j.bspc.2026.110753_b37","unstructured":"Based on audio-video evoked auditory attention detection electroencephalogram dataset."},{"issue":"1","key":"10.1016\/j.bspc.2026.110753_b38","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1109\/TBME.2023.3294242","article-title":"Brain topology modeling with EEG-graphs for auditory spatial attention detection","volume":"71","author":"Cai","year":"2023","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"10.1016\/j.bspc.2026.110753_b39","doi-asserted-by":"crossref","first-page":"106580","DOI":"10.1016\/j.neunet.2024.106580","article-title":"DGSD: Dynamical graph self-distillation for EEG-based auditory spatial attention detection","volume":"179","author":"Fan","year":"2024","journal-title":"Neural Netw."},{"issue":"Nov","key":"10.1016\/j.bspc.2026.110753_b40","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["Biomedical Signal Processing and Control"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1746809426013078?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1746809426013078?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T20:09:04Z","timestamp":1783022944000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1746809426013078"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":40,"alternative-id":["S1746809426013078"],"URL":"https:\/\/doi.org\/10.1016\/j.bspc.2026.110753","relation":{},"ISSN":["1746-8094"],"issn-type":[{"value":"1746-8094","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MSTFF-Net: Multi-scale spatio-temporal\u2013frequency feature fusion for auditory attention detection","name":"articletitle","label":"Article Title"},{"value":"Biomedical Signal Processing and Control","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.bspc.2026.110753","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":"110753"}}