{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T03:50:41Z","timestamp":1776743441696,"version":"3.51.2"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T00:00:00Z","timestamp":1741651200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T00:00:00Z","timestamp":1741651200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s11760-025-03968-1","type":"journal-article","created":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T15:18:20Z","timestamp":1741706300000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Mitigating cross-scenario challenges in voiceprint recognition: a dual-channel approach"],"prefix":"10.1007","volume":"19","author":[{"given":"Huajun","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuqi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,3,11]]},"reference":[{"key":"3968_CR1","doi-asserted-by":"crossref","unstructured":"Rouvier, M., Dufour, R., Bousquet, P. M.: Review of different robust x-vector extractors for speaker verification. In: 2020 28th European Signal Processing Conference (EUSIPCO), pp. 1\u20135. IEEE (2021)","DOI":"10.23919\/Eusipco47968.2020.9287426"},{"key":"3968_CR2","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lv, Z., Wu, H., et al.: Mfa-conformer: multi-scale feature aggregation conformer for automatic speaker verification. arXiv preprint arXiv:2203.15249 (2022)","DOI":"10.21437\/Interspeech.2022-563"},{"issue":"15","key":"3968_CR3","doi-asserted-by":"publisher","first-page":"3309","DOI":"10.3390\/electronics12153309","volume":"12","author":"S Gui","year":"2023","unstructured":"Gui, S., Zhou, C., Wang, H., et al.: Application of voiceprint recognition technology based on channel confrontation training in the field of information security. Electronics 12(15), 3309 (2023)","journal-title":"Electronics"},{"issue":"5","key":"3968_CR4","doi-asserted-by":"publisher","first-page":"3359","DOI":"10.3390\/app13053359","volume":"13","author":"SA Li","year":"2023","unstructured":"Li, S.A., Liu, Y.Y., Chen, Y.C., et al.: Voice interaction recognition design in real-life scenario mobile robot applications. Appl. Sci. 13(5), 3359 (2023)","journal-title":"Appl. Sci."},{"issue":"16","key":"3968_CR5","doi-asserted-by":"publisher","first-page":"8152","DOI":"10.3390\/app12168152","volume":"12","author":"S Cheng","year":"2022","unstructured":"Cheng, S., Shen, Y., Wang, D.: Target speaker extraction by fusing voiceprint features. Appl. Sci. 12(16), 8152 (2022)","journal-title":"Appl. Sci."},{"key":"3968_CR6","doi-asserted-by":"publisher","first-page":"109153","DOI":"10.1016\/j.compeleceng.2024.109153","volume":"116","author":"H Kibriya","year":"2024","unstructured":"Kibriya, H., Siddiqa, A., Khan, W.Z., et al.: Towards safer online communities: deep learning and explainable AI for hate speech detection and classification. Comput. Electr. Eng. 116, 109153 (2024)","journal-title":"Comput. Electr. Eng."},{"key":"3968_CR7","doi-asserted-by":"crossref","unstructured":"Li, Z., Liu, Y., Li, L., et al.: Additive phoneme-aware margin softmax loss for language recognition. arXiv preprint arXiv:2106.12851 (2021)","DOI":"10.21437\/Interspeech.2021-1167"},{"key":"3968_CR8","doi-asserted-by":"publisher","first-page":"117","DOI":"10.14801\/jkiit.2022.20.11.117","volume":"20","author":"HJ Kwon","year":"2022","unstructured":"Kwon, H.J., Ok, S.H.: A lightweight identity recognition network using the ArcFace. J. Korean Inst. Inform. Technol. 20, 117 (2022). https:\/\/doi.org\/10.14801\/jkiit.2022.20.11.117","journal-title":"J. Korean Inst. Inform. Technol."},{"key":"3968_CR9","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., et al.: Arcface: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"3968_CR10","doi-asserted-by":"crossref","unstructured":"Br\u00fcmmer, N., Swart, A., Mo\u0161ner, L., et al.: Probabilistic spherical discriminant analysis: an alternative to PLDA for length-normalized embeddings. arXiv preprint arXiv:2203.14893 (2022)","DOI":"10.21437\/Interspeech.2022-731"},{"key":"3968_CR11","doi-asserted-by":"crossref","unstructured":"Sang, M., Hansen, J.H.L.: Multi-frequency information enhanced channel attention module for speaker representation learning. In: Proceedings of the Interspeech 2022, Incheon, Korea, pp. 321\u2013325 (2022)","DOI":"10.21437\/Interspeech.2022-892"},{"key":"3968_CR12","doi-asserted-by":"publisher","first-page":"109166","DOI":"10.1016\/j.compeleceng.2024.109166","volume":"116","author":"D Bai","year":"2024","unstructured":"Bai, D., Li, G., Jiang, D., et al.: Depth feature fusion based surface defect region identification method for steel plate manufacturing. Comput. Electr. Eng. 116, 109166 (2024)","journal-title":"Comput. Electr. Eng."},{"key":"3968_CR13","doi-asserted-by":"publisher","first-page":"3995","DOI":"10.3390\/app10113995","volume":"10","author":"W Yao","year":"2020","unstructured":"Yao, W., Xu, Y., Qian, Y., et al.: A classification system for insulation defect identification of gas-insulated switchgear (GIS), based on voiceprint recognition technology. Appl. Sci. 10, 3995 (2020)","journal-title":"Appl. Sci."},{"key":"3968_CR14","doi-asserted-by":"publisher","first-page":"108021","DOI":"10.1016\/j.triboint.2022.108021","volume":"178","author":"I Argatov","year":"2023","unstructured":"Argatov, I., Jin, X.: Time-delay neural network modeling of the running-in wear process. Tribol. Int. 178, 108021 (2023)","journal-title":"Tribol. Int."},{"key":"3968_CR15","doi-asserted-by":"crossref","unstructured":"Desplanques, B., Thienpondt, J., Demuynck, K.: Ecapa-tdnn: emphasized channel attention, propagation and aggregation in tdnn based speaker verification. arXiv preprint arXiv:2005.07143 (2020)","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"3968_CR16","unstructured":"Liu, W., Wen, Y., Yu, Z., et al.: Large-margin softmax loss for convolutional neural networks. arXiv preprint arXiv:1612.02295 (2016)"},{"issue":"7","key":"3968_CR17","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1109\/LSP.2018.2822810","volume":"25","author":"F Wang","year":"2018","unstructured":"Wang, F., Cheng, J., Liu, W., et al.: Additive margin softmax for face verification. IEEE Signal Process. Lett. 25(7), 926\u2013930 (2018)","journal-title":"IEEE Signal Process. Lett."},{"key":"3968_CR18","doi-asserted-by":"crossref","unstructured":"Zhou, D., Wang, L., Lee, K.A., et al.: Dynamic margin softmax loss for speaker verification. In: INTERSPEECH, pp. 3800\u20133804 (2020)","DOI":"10.21437\/Interspeech.2020-1106"},{"key":"3968_CR19","doi-asserted-by":"publisher","first-page":"109274","DOI":"10.1016\/j.compeleceng.2024.109274","volume":"117","author":"S Agac","year":"2024","unstructured":"Agac, S., Incel, O.D.: Resource-efficient, sensor-based human activity recognition with lightweight deep models boosted with attention. Comput. Electr. Eng. 117, 109274 (2024)","journal-title":"Comput. Electr. Eng."},{"key":"3968_CR20","doi-asserted-by":"crossref","unstructured":"Zhou, T., Zhao, Y., Wu, J.: Resnext and res2net structures for speaker verification. In: 2021 IEEE Spoken Language Technology Workshop (SLT), pp. 301\u2013307 (2020)","DOI":"10.1109\/SLT48900.2021.9383531"},{"issue":"2","key":"3968_CR21","doi-asserted-by":"publisher","first-page":"263","DOI":"10.3390\/jmse11020263","volume":"11","author":"J Wu","year":"2023","unstructured":"Wu, J., Li, P., Wang, V.F.R., et al.: The underwater acoustic target recognition using cross-domain pre-training with fbank fusion features. J. Mar. Sci. Eng. 11(2), 263 (2023)","journal-title":"J. Mar. Sci. Eng."},{"key":"3968_CR22","unstructured":"Qin, Z., Sun, W., Deng, et al.: Cosformer: rethinking softmax in attention. arXiv preprint arXiv:2202.08791"},{"key":"3968_CR23","doi-asserted-by":"publisher","first-page":"106675","DOI":"10.1016\/j.compag.2021.106675","volume":"193","author":"B Xu","year":"2022","unstructured":"Xu, B., Wang, W., Guo, L., et al.: CattleFaceNet: a cattle face identification approach based on RetinaFace and ArcFace loss. Comput. Electron. Agric. 193, 106675 (2022)","journal-title":"Comput. Electron. Agric."},{"key":"3968_CR24","doi-asserted-by":"crossref","unstructured":"Wang, Y., Bai, H., Stanton, M., et al.: Plda: parallel latent dirichlet allocation for large-scale applications. In: International Conference on Algorithmic Applications in Management, pp. 301\u2013314. Springer Berlin Heidelberg, Berlin, Heidelberg","DOI":"10.1007\/978-3-642-02158-9_26"},{"key":"3968_CR25","unstructured":"Simb\u00fcrger, W., Powierski, R.: ZofzPCB Gerber to STEP export for advanced EM FEM simulation"},{"key":"3968_CR26","doi-asserted-by":"publisher","DOI":"10.1007\/s12204-024-2726-z","author":"S Liu","year":"2024","unstructured":"Liu, S., Song, Z., He, L.: Improving ECAPA-TDNN performance with coordinate attention. J. Shanghai Jiaotong Univ. (Sci.) (2024). https:\/\/doi.org\/10.1007\/s12204-024-2726-z","journal-title":"J. Shanghai Jiaotong Univ. (Sci.)"},{"key":"3968_CR27","doi-asserted-by":"crossref","unstructured":"Zhou, T., Zhao, Y., Wu, J.: Resnext and res2net structures for speaker verification. In: 2021 IEEE Spoken Language Technology Workshop (SLT), pp. 301\u2013307","DOI":"10.1109\/SLT48900.2021.9383531"},{"issue":"2","key":"3968_CR28","doi-asserted-by":"publisher","first-page":"1371","DOI":"10.1007\/s11063-022-10944-0","volume":"55","author":"C Yang","year":"2022","unstructured":"Yang, C., Wang, X., Yao, L., et al.: Attentional gated Res2Net for multivariate time series classification. Neural. Process. Lett. 55(2), 1371\u20131395 (2022)","journal-title":"Neural. Process. Lett."},{"key":"3968_CR29","unstructured":"Huh, J., Brown, A., Jung, J. W., et al.: Garcia-Romero, D., Zisserman, A.: Voxsrc 2022: the fourth voxceleb speaker recognition challenge. arXiv preprint arXiv:2302.10248 (2023)"},{"issue":"19","key":"3968_CR30","doi-asserted-by":"publisher","first-page":"4205","DOI":"10.3390\/math11194205","volume":"11","author":"S Wang","year":"2023","unstructured":"Wang, S., Zhang, H., Zhang, X., et al.: Voiceprint recognition under cross-scenario conditions using perceptual wavelet packet entropy-guided efficient-channel-attention\u2013Res2Net\u2013time-delay-neural-network model. Mathematics 11(19), 4205 (2023)","journal-title":"Mathematics"},{"key":"3968_CR31","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1016\/j.bspc.2018.10.014","volume":"49","author":"Y Tsao","year":"2019","unstructured":"Tsao, Y., Lin, T.-H., Chen, F., Chang, Y.-F., Cheng, C.-H., Tsai, K.-H.: Robust S1 and S2 heart sound recognition based on spectral restoration and multi-style training. Biomed. Signal Process. Control 49, 173\u2013180 (2019)","journal-title":"Biomed. Signal Process. Control"},{"key":"3968_CR32","doi-asserted-by":"publisher","first-page":"1208","DOI":"10.1109\/LSP.2017.2713830","volume":"24","author":"J Lee","year":"2017","unstructured":"Lee, J., Nam, J.: Multi-level and multi-scale feature aggregation using pretrained convolutional neural networks for music auto-tagging. IEEE Signal Process. Lett. 24, 1208\u20131212 (2017)","journal-title":"IEEE Signal Process. Lett."}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-03968-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-025-03968-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-03968-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T20:12:44Z","timestamp":1744143164000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-025-03968-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,11]]},"references-count":32,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["3968"],"URL":"https:\/\/doi.org\/10.1007\/s11760-025-03968-1","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,11]]},"assertion":[{"value":"24 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 February 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 February 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 March 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"402"}}