{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T17:03:21Z","timestamp":1793379801229,"version":"4.5.0"},"reference-count":49,"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":["Information Fusion"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.inffus.2026.104358","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T23:31:41Z","timestamp":1775604701000},"page":"104358","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["LHCC: Cross-domain audio deepfake detection via consistency-aware fusion of acoustic and semantic representations"],"prefix":"10.1016","volume":"134","author":[{"given":"Guofu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaopin","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kejiang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7765-9239","authenticated-orcid":false,"given":"Yaofei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.inffus.2026.104358_bib0001","doi-asserted-by":"crossref","DOI":"10.3389\/fdata.2022.1001063","article-title":"Audio deepfakes: a survey","volume":"5","author":"Khanjani","year":"2023","journal-title":"Front. Big Data"},{"key":"10.1016\/j.inffus.2026.104358_bib0002","doi-asserted-by":"crossref","unstructured":"Y. Wang, R. J. Skerry-Ryan, D. Stanton, Y. Wu, R. J. Weiss, N. Jaitly, Z. Yang, Y. Xiao, Z. Chen, S. Bengio, et al., Tacotron: towards end-to-end speech synthesis, arXiv: 1703.10135(2017).","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"10.1016\/j.inffus.2026.104358_bib0003","first-page":"3165","article-title":"Fastspeech: fast, robust and controllable text to speech","volume":"32","author":"Ren","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104358_bib0004","series-title":"2018 26th European Signal Processing Conference (EUSIPCO)","first-page":"2100","article-title":"Cyclegan-vc: non-parallel voice conversion using cycle-consistent adversarial networks","author":"Kaneko","year":"2018"},{"key":"10.1016\/j.inffus.2026.104358_bib0005","series-title":"International Conference on Machine Learning","first-page":"5210","article-title":"Autovc: zero-shot voice style transfer with only autoencoder loss","author":"Qian","year":"2019"},{"key":"10.1016\/j.inffus.2026.104358_bib0006","series-title":"Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security","first-page":"2696","article-title":"\u201d Better be computer or I\u2019m dumb\u201d: a large-scale evaluation of humans as audio deepfake detectors","author":"Warren","year":"2024"},{"key":"10.1016\/j.inffus.2026.104358_bib0007","unstructured":"M. Li, Y. Ahmadiadli, X.-P. Zhang, Audio anti-spoofing detection: a survey, arXiv: 2404.13914(2024)."},{"key":"10.1016\/j.inffus.2026.104358_bib0008","doi-asserted-by":"crossref","first-page":"516","DOI":"10.1016\/j.csl.2017.01.001","article-title":"Constant Q cepstral coefficients: a spoofing countermeasure for automatic speaker verification","volume":"45","author":"Todisco","year":"2017","journal-title":"Compu. Speech Language"},{"issue":"4","key":"10.1016\/j.inffus.2026.104358_bib0009","doi-asserted-by":"crossref","first-page":"768","DOI":"10.1109\/TASLP.2016.2526653","article-title":"Anti-spoofing for text-independent speaker verification: an initial database, comparison of countermeasures, and human performance","volume":"24","author":"Wu","year":"2016","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.inffus.2026.104358_bib0010","series-title":"Interspeech 2018","first-page":"77","article-title":"Integrated presentation attack detection and automatic speaker verification: common features and Gaussian back-end fusion","author":"Todisco","year":"2018"},{"key":"10.1016\/j.inffus.2026.104358_bib0011","doi-asserted-by":"crossref","unstructured":"M. Alzantot, Z. Wang, M.B. Srivastava, Deep residual neural networks for audio spoofing detection, arXiv: 1907.00501(2019).","DOI":"10.21437\/Interspeech.2019-3174"},{"key":"10.1016\/j.inffus.2026.104358_bib0012","doi-asserted-by":"crossref","unstructured":"Z. Wu, R.K. Das, J. Yang, H. Li, Light convolutional neural network with feature genuinization for detection of synthetic speech attacks, arXiv: 2009.09637(2020).","DOI":"10.21437\/Interspeech.2020-1810"},{"key":"10.1016\/j.inffus.2026.104358_bib0013","doi-asserted-by":"crossref","unstructured":"H. Tak, J.-w. Jung, J. Patino, M. Kamble, M. Todisco, N. Evans, End-to-end spectro-temporal graph attention networks for speaker verification anti-spoofing and speech deepfake detection, arXiv: 2107.12710(2021).","DOI":"10.21437\/ASVSPOOF.2021-1"},{"key":"10.1016\/j.inffus.2026.104358_bib0014","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.inffus.2026.104358_bib0015","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.inffus.2026.104358_bib0016","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."},{"key":"10.1016\/j.inffus.2026.104358_bib0017","doi-asserted-by":"crossref","unstructured":"H. Tak, M. Todisco, X. Wang, J.-w. Jung, J. Yamagishi, N. Evans, Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation, arXiv: 2202.12233(2022).","DOI":"10.21437\/Odyssey.2022-16"},{"key":"10.1016\/j.inffus.2026.104358_bib0018","unstructured":"J. Yamagishi, M. Todisco, M. Sahidullah, H. Delgado, X. Wang, N. Evans, T. Kinnunen, K.A. Lee, V. Vestman, A. Nautsch, Asvspoof 2019: the 3rd automatic speaker verification spoofing and countermeasures challenge database (2019)."},{"key":"10.1016\/j.inffus.2026.104358_bib0019","doi-asserted-by":"crossref","unstructured":"J. Yamagishi, X. Wang, M. Todisco, M. Sahidullah, J. Patino, A. Nautsch, X. Liu, K.A. Lee, T. Kinnunen, N. Evans, et al., ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection, arXiv: 2109.00537(2021).","DOI":"10.21437\/ASVSPOOF.2021-8"},{"key":"10.1016\/j.inffus.2026.104358_bib0020","doi-asserted-by":"crossref","first-page":"813","DOI":"10.1109\/TASLP.2022.3233236","article-title":"The partialspoof database and countermeasures for the detection of short fake speech segments embedded in an utterance","volume":"31","author":"Zhang","year":"2022","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.inffus.2026.104358_bib0021","doi-asserted-by":"crossref","unstructured":"N.M. M\u00fcller, P. Czempin, F. Dieckmann, A. Froghyar, K. B\u00f6ttinger, Does audio deepfake detection generalize?, arXiv: 2203.16263(2022).","DOI":"10.21437\/Interspeech.2022-108"},{"key":"10.1016\/j.inffus.2026.104358_bib0022","unstructured":"H. Khalid, S. Tariq, M. Kim, S.S. Woo, FakeAVCeleb: a novel audio-video multimodal deepfake dataset, arXiv: 2108.05080(2021)."},{"key":"10.1016\/j.inffus.2026.104358_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101869","article-title":"A review of deep learning techniques for speech processing","volume":"99","author":"Mehrish","year":"2023","journal-title":"Inf. Fusion"},{"issue":"5","key":"10.1016\/j.inffus.2026.104358_bib0024","doi-asserted-by":"crossref","first-page":"155","DOI":"10.3390\/a15050155","article-title":"A review of modern audio deepfake detection methods: challenges and future directions","volume":"15","author":"Almutairi","year":"2022","journal-title":"Algorithms"},{"key":"10.1016\/j.inffus.2026.104358_bib0025","doi-asserted-by":"crossref","first-page":"7133","DOI":"10.1109\/TIFS.2024.3431888","article-title":"Audio multi-view spoofing detection framework based on audio-text-emotion correlations","volume":"19","author":"Wu","year":"2024","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.inffus.2026.104358_bib0026","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103097","article-title":"Hierarchical multi-source cues fusion for mono-to-binaural based audio deepfake detection","volume":"120","author":"Liu","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104358_bib0027","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103738","article-title":"Dual-level principal component fusion networks for synthetic speech detection","volume":"127","author":"Mai","year":"2026","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104358_bib0028","series-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"13131","article-title":"A robust audio deepfake detection system via multi-view feature","author":"Yang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104358_bib0029","doi-asserted-by":"crossref","first-page":"1705","DOI":"10.21437\/Interspeech.2016-1326","article-title":"Cross-database evaluation of audio-based spoofing detection systems","author":"Korshunov","year":"2016","journal-title":"Interspeech 2016"},{"key":"10.1016\/j.inffus.2026.104358_bib0030","series-title":"Odyssey","first-page":"132","article-title":"Generalization of audio deepfake detection","author":"Chen","year":"2020"},{"key":"10.1016\/j.inffus.2026.104358_bib0031","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.inffus.2026.104358_bib0032","doi-asserted-by":"crossref","unstructured":"H. Ma, J. Yi, J. Tao, Y. Bai, Z. Tian, C. Wang, Continual learning for fake audio detection, arXiv: 2104.07286(2021).","DOI":"10.21437\/Interspeech.2021-794"},{"key":"10.1016\/j.inffus.2026.104358_bib0033","series-title":"International Conference on Machine Learning","first-page":"41819","article-title":"Do you remember? Overcoming catastrophic forgetting for fake audio detection","author":"Zhang","year":"2023"},{"key":"10.1016\/j.inffus.2026.104358_bib0034","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.inffus.2026.104358_bib0035","doi-asserted-by":"crossref","unstructured":"P. Kawa, M. Plata, P. Syga, Attack agnostic dataset: towards generalization and stabilization of audio deepfake detection, arXiv: 2206.13979(2022).","DOI":"10.21437\/Interspeech.2022-10078"},{"key":"10.1016\/j.inffus.2026.104358_bib0036","series-title":"ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"6359","article-title":"A capsule network based approach for detection of audio spoofing attacks","author":"Luo","year":"2021"},{"key":"10.1016\/j.inffus.2026.104358_bib0037","series-title":"2021 IEEE International Conference on Image Processing (ICIP)","first-page":"3907","article-title":"Recalibrated bandpass filtering on temporal waveform for audio spoof detection","author":"Ren","year":"2021"},{"key":"10.1016\/j.inffus.2026.104358_bib0038","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia","first-page":"7395","article-title":"Coarse-to-fine proposal refinement framework for audio temporal forgery detection and localization","author":"Wu","year":"2024"},{"key":"10.1016\/j.inffus.2026.104358_bib0039","series-title":"2010 7th International Symposium on Chinese Spoken Language Processing","first-page":"309","article-title":"Speaker verification against synthetic speech","author":"Chen","year":"2010"},{"key":"10.1016\/j.inffus.2026.104358_bib0040","series-title":"2013 IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS)","first-page":"1","article-title":"A one-class classification approach to generalised speaker verification spoofing countermeasures using local binary patterns","author":"Alegre","year":"2013"},{"key":"10.1016\/j.inffus.2026.104358_bib0041","series-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1406","article-title":"Multi-scale permutation entropy for audio deepfake detection","author":"Wang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104358_bib0042","doi-asserted-by":"crossref","unstructured":"A. Babu, C. Wang, A. Tjandra, K. Lakhotia, Q. Xu, N. Goyal, K. Singh, P. Von Platen, Y. Saraf, J. Pino, et al., XLS-R: self-supervised cross-lingual speech representation learning at scale, arXiv: 2111.09296(2021).","DOI":"10.21437\/Interspeech.2022-143"},{"key":"10.1016\/j.inffus.2026.104358_bib0043","series-title":"ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"9241","article-title":"The vicomtech audio deepfake detection system based on wav2vec2 for the 2022\u202fADD challenge","author":"Mart\u00edn-Do\u00f1as","year":"2022"},{"key":"10.1016\/j.inffus.2026.104358_bib0044","series-title":"2019 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","first-page":"1","article-title":"For: a dataset for synthetic speech detection","author":"Reimao","year":"2019"},{"key":"10.1016\/j.inffus.2026.104358_bib0045","series-title":"International Conference on Machine Learning","first-page":"3519","article-title":"Similarity of neural network representations revisited","author":"Kornblith","year":"2019"},{"key":"10.1016\/j.inffus.2026.104358_bib0046","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.inffus.2026.104358_bib0047","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia","first-page":"6765","article-title":"Audio deepfake detection with self-supervised xls-r and sls classifier","author":"Zhang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104358_bib0048","series-title":"Interspeech","first-page":"4828","article-title":"Towards generalisable and calibrated audio deepfake detection with self-supervised representations","author":"Pascu","year":"2024"},{"key":"10.1016\/j.inffus.2026.104358_bib0049","doi-asserted-by":"crossref","first-page":"12005","DOI":"10.1109\/TIFS.2025.3626963","article-title":"Nes2Net: a lightweight nested architecture for foundation model driven speech anti-spoofing","volume":"20","author":"Liu","year":"2025","journal-title":"IEEE Trans. Inf. Forensics Secur."}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S156625352600237X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S156625352600237X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T11:41:46Z","timestamp":1779190906000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S156625352600237X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":49,"alternative-id":["S156625352600237X"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104358","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"LHCC: Cross-domain audio deepfake detection via consistency-aware fusion of acoustic and semantic representations","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104358","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"104358"}}