{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T07:56:04Z","timestamp":1781510164577,"version":"3.54.1"},"reference-count":41,"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"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neucom.2026.134173","type":"journal-article","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T23:27:23Z","timestamp":1780356443000},"page":"134173","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["HRWA-conformer: Hybrid ring-window attention with multi-kernel temporal modeling for synthetic speech detection"],"prefix":"10.1016","volume":"697","author":[{"given":"Tingting","family":"Luo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sicong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134173_bib0005","series-title":"2020 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","first-page":"1","article-title":"Deepfake detection: current challenges and next steps","author":"Lyu","year":"2020"},{"key":"10.1016\/j.neucom.2026.134173_bib0010","series-title":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","first-page":"1771","article-title":"ASR model adaptation for rare words using synthetic data generated by multiple text-to-speech systems","author":"Yuen","year":"2023"},{"key":"10.1016\/j.neucom.2026.134173_bib0015","doi-asserted-by":"crossref","first-page":"2072","DOI":"10.1177\/1461444820925811","article-title":"Anticipating and addressing the ethical implications of deepfakes in the context of elections","volume":"23","author":"Diakopoulos","year":"2021","journal-title":"New Media Soc."},{"key":"10.1016\/j.neucom.2026.134173_bib0020","series-title":"Proc. ASVspoof 2024","first-page":"123","article-title":"AASIST3: KAN-enhanced AASIST speech deepfake detection using SSL features and additional regularization for the ASVspoof 2024 challenge","author":"Borodin","year":"2024"},{"key":"10.1016\/j.neucom.2026.134173_bib0025","series-title":"ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"Identifying source speakers for voice conversion based spoofing attacks on speaker verification systems","author":"Cai","year":"2023"},{"key":"10.1016\/j.neucom.2026.134173_bib0030","series-title":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","first-page":"115","article-title":"Synthetic voice detection and audio splicing detection using se-RES2net-conformer architecture","author":"Wang","year":"2022"},{"key":"10.1016\/j.neucom.2026.134173_bib0035","article-title":"An explainable deepfake of speech detection method with spectrograms and waveforms","volume":"81","author":"Yu","year":"2024","journal-title":"J. Inf. Secur. Appl."},{"key":"10.1016\/j.neucom.2026.134173_bib0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.124974","article-title":"Do not ignore heterogeneity and heterophily: multi-network collaborative telecom fraud detection","volume":"257","author":"Ren","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.neucom.2026.134173_bib0045","series-title":"ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"BTS-E: audio deepfake detection using breathing-talking-silence encoder","author":"Doan","year":"2023"},{"key":"10.1016\/j.neucom.2026.134173_bib0050","doi-asserted-by":"crossref","DOI":"10.7717\/peerj-cs.2037","article-title":"Deepfake forensics: a survey of digital forensic methods for multimodal deepfake identification on social media","volume":"10","author":"Qureshi","year":"2024","journal-title":"Peerj Comput. Sci."},{"key":"10.1016\/j.neucom.2026.134173_bib0055","series-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"11251","article-title":"One-class knowledge distillation for spoofing speech detection","author":"Lu","year":"2024"},{"key":"10.1016\/j.neucom.2026.134173_bib0060","doi-asserted-by":"crossref","first-page":"1462","DOI":"10.1109\/LSP.2022.3183951","article-title":"Synthetic speech detection based on local autoregression and variance statistics","volume":"29","author":"Cui","year":"2022","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.neucom.2026.134173_bib0065","series-title":"2022 30th European Signal Processing Conference (EUSIPCO)","first-page":"369","article-title":"Energy separation based instantaneous frequency estimation from quadrature and in-phase components for replay spoof detection","author":"Gupta","year":"2022"},{"key":"10.1016\/j.neucom.2026.134173_bib0070","doi-asserted-by":"crossref","first-page":"937","DOI":"10.1109\/LSP.2021.3076358","article-title":"One-class learning towards synthetic voice spoofing detection","volume":"28","author":"Zhang","year":"2021","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.neucom.2026.134173_bib0075","series-title":"ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"6354","article-title":"Replay and synthetic speech detection with RES2net architecture","author":"Li","year":"2021"},{"key":"10.1016\/j.neucom.2026.134173_bib0080","series-title":"2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","first-page":"1684","article-title":"A light CNN with split batch normalization for spoofed speech detection using data augmentation","author":"Lin","year":"2022"},{"key":"10.1016\/j.neucom.2026.134173_bib0085","series-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"12101","article-title":"GMM-ResNet2: ensemble of group ResNet networks for synthetic speech detection","author":"Lei","year":"2024"},{"key":"10.1016\/j.neucom.2026.134173_bib0090","series-title":"Interspeech 2020","first-page":"5036","article-title":"Conformer: convolution-augmented transformer for speech recognition","author":"Gulati","year":"2020"},{"key":"10.1016\/j.neucom.2026.134173_bib0095","series-title":"ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"6367","article-title":"Aasist: audio anti-spoofing using integrated spectro-temporal graph attention networks","author":"Jung","year":"2022"},{"key":"10.1016\/j.neucom.2026.134173_bib0100","series-title":"Proc. Interspeech, 2023","first-page":"5281","article-title":"A conformer-based classifier for variable-length utterance processing in anti-spoofing","author":"Rosello","year":"2023"},{"key":"10.1016\/j.neucom.2026.134173_bib0105","series-title":"INTERSPEECH","first-page":"3558","article-title":"Overlapped frequency-distributed network: frequency-aware voice spoofing countermeasure","author":"Choi","year":"2022"},{"key":"10.1016\/j.neucom.2026.134173_bib0110","series-title":"2023 International Conference on Computer Applications Technology (CCAT)","first-page":"104","article-title":"Enhancing synthesized speech detection with dual attention using features fusion","author":"Wang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134173_bib0115","series-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"10156","article-title":"Robust spoof speech detection based on multi-scale feature aggregation and dynamic convolution","author":"Wu","year":"2024"},{"key":"10.1016\/j.neucom.2026.134173_bib0120","series-title":"Interspeech 2024","first-page":"537","article-title":"Temporal-channel modeling in multi-head self-attention for synthetic speech detection","author":"Truong","year":"2024"},{"key":"10.1016\/j.neucom.2026.134173_bib0125","author":"Hong"},{"key":"10.1016\/j.neucom.2026.134173_bib0130","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.neucom.2026.134173_bib0135","series-title":"Interspeech 2024","article-title":"Multi-convformer: extending conformer with multiple convolution kernels","author":"Prabhu","year":"2024"},{"key":"10.1016\/j.neucom.2026.134173_bib0140","series-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"10581","article-title":"HM-conformer: a conformer-based audio deepfake detection system with hierarchical pooling and multi-level classification token aggregation methods","author":"Shin","year":"2024"},{"key":"10.1016\/j.neucom.2026.134173_bib0145","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.neucom.2026.134173_bib0150","series-title":"Interspeech 2022","first-page":"2278","article-title":"XLS-R: self-supervised cross-lingual speech representation learning at scale","author":"Babu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134173_bib0155","series-title":"Interspeech 2019","article-title":"ASVspoof 2019: future horizons in spoofed and fake audio detection","author":"Todisco","year":"2019"},{"key":"10.1016\/j.neucom.2026.134173_bib0160","doi-asserted-by":"crossref","first-page":"2507","DOI":"10.1109\/TASLP.2023.3285283","article-title":"Asvspoof 2021: towards spoofed and deepfake speech detection in the wild","volume":"31","author":"Liu","year":"2023","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.neucom.2026.134173_bib0165","author":"Br\u00fcmmer"},{"key":"10.1016\/j.neucom.2026.134173_bib0170","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.neucom.2026.134173_bib0175","series-title":"Odyssey 2022: The Speaker and Language Recognition Workshop","article-title":"Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation","author":"Tak","year":"2022"},{"key":"10.1016\/j.neucom.2026.134173_bib0180","series-title":"ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"6382","article-title":"Rawboost: a raw data boosting and augmentation method applied to automatic speaker verification anti-spoofing","author":"Tak","year":"2022"},{"key":"10.1016\/j.neucom.2026.134173_bib0185","series-title":"ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"6369","article-title":"End-to-end anti-spoofing with rawnet2","author":"Tak","year":"2021"},{"key":"10.1016\/j.neucom.2026.134173_bib0190","series-title":"ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"Mixture of experts fusion for fake audio detection using frozen wav2vec 2.0","author":"Wang","year":"2025"},{"key":"10.1016\/j.neucom.2026.134173_bib0195","series-title":"Odyssey 2022: The Speaker and Language Recognition Workshop","article-title":"Investigating self-supervised front ends for speech spoofing countermeasures","author":"Wang","year":"2022"},{"key":"10.1016\/j.neucom.2026.134173_bib0200","series-title":"Proceedings of the 33rd ACM International Conference on Multimedia","article-title":"ALDEN: dual-level disentanglement with meta-learning for generalizable audio deepfake detection","author":"Xu","year":"2025"},{"key":"10.1016\/j.neucom.2026.134173_bib0205","series-title":"ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"DiffSSD: a diffusion-based dataset for speech forensics","author":"Bhagtani","year":"2025"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226015717?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226015717?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T07:48:11Z","timestamp":1781509691000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226015717"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":41,"alternative-id":["S0925231226015717"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134173","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"HRWA-conformer: Hybrid ring-window attention with multi-kernel temporal modeling for synthetic speech detection","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134173","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"134173"}}