{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T08:38:31Z","timestamp":1767861511475,"version":"3.49.0"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T00:00:00Z","timestamp":1726704000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T00:00:00Z","timestamp":1726704000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["RGPIN-2018-05221"],"award-info":[{"award-number":["RGPIN-2018-05221"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s00034-024-02854-4","type":"journal-article","created":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T18:02:34Z","timestamp":1726768954000},"page":"534-555","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Attentive Context-Aware Deep Speaker Representations for Voice Biometrics in Adverse Conditions"],"prefix":"10.1007","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1764-9078","authenticated-orcid":false,"given":"Zhor","family":"Benhafid","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0731-2632","authenticated-orcid":false,"given":"Sid Ahmed","family":"Selouani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abderrahmane","family":"Amrouche","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammed","family":"Sidi Yakoub","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,19]]},"reference":[{"issue":"5","key":"2854_CR1","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1109\/LSP.2006.870086","volume":"13","author":"WM Campbell","year":"2006","unstructured":"W.M. Campbell, D.E. Sturim, D.A. Reynolds, Support vector machines using GMM supervectors for speaker verification. IEEE Signal Process. Lett. 13(5), 308\u2013311 (2006). https:\/\/doi.org\/10.1109\/LSP.2006.870086","journal-title":"IEEE Signal Process. Lett."},{"key":"2854_CR2","doi-asserted-by":"publisher","unstructured":"C.P. Chen, S.Y. Zhang, C.T. Yeh, J.C. Wang, T. Wang, C.L. Huang, Speaker characterization using TDNN-LSTM based speaker embedding. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing\u2013Proceedings (2019), p. 6211\u20136215. https:\/\/doi.org\/10.1109\/ICASSP.2019.8683185","DOI":"10.1109\/ICASSP.2019.8683185"},{"issue":"1","key":"2854_CR3","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1229\/1\/012077","volume":"1229","author":"K Chen","year":"2019","unstructured":"K. Chen, W. Zhang, D. Chen, X. Huang, B. Liu, X. Xu, Gated time delay neural network for speech recognition. J. Phys. Conf. Ser. 1229(1), 012077 (2019). https:\/\/doi.org\/10.1088\/1742-6596\/1229\/1\/012077","journal-title":"J. Phys. Conf. Ser."},{"issue":"3","key":"2854_CR4","doi-asserted-by":"publisher","first-page":"2853","DOI":"10.21437\/Interspeech.2018-70","volume":"1","author":"P Chen","year":"2018","unstructured":"P. Chen, W. Guo, Z. Chen, J. Sun, L. You, Gated convolutional neural network for sentence matching. Interspeech 1(3), 2853\u20132857 (2018). https:\/\/doi.org\/10.21437\/Interspeech.2018-70","journal-title":"Interspeech"},{"key":"2854_CR5","doi-asserted-by":"publisher","first-page":"1243","DOI":"10.1109\/TASLP.2021.3065202","volume":"29","author":"X Chen","year":"2021","unstructured":"X. Chen, C. Bao, Phoneme-unit-specific time-delay neural network for speaker verification. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 1243\u20131255 (2021). https:\/\/doi.org\/10.1109\/TASLP.2021.3065202","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"2854_CR6","doi-asserted-by":"publisher","unstructured":"S. Choi, S. Chung, S. Lee, S. Han, T. Kang, J. Seo, I.-Y. Kwak, S. Oh, TB-ResNet: bridging the Gap from TDNN to ResNet in automatic speaker verification with temporal-bottleneck enhancement. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing\u2013Proceedings (2024), p. 10291\u201310295. https:\/\/doi.org\/10.1109\/ICASSP48485.2024.10448221","DOI":"10.1109\/ICASSP48485.2024.10448221"},{"key":"2854_CR7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1929","author":"JS Chung","year":"2018","unstructured":"J.S. Chung, A. Nagrani, A. Zisserman, VoxCeleb2: deep speaker recognition. Interspeech (2018). https:\/\/doi.org\/10.21437\/interspeech.2018-1929","journal-title":"Interspeech"},{"issue":"4","key":"2854_CR8","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2011","unstructured":"N. Dehak, P.J. Kenny, R. Dehak, P. Dumouchel, P. Ouellet, Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 19(4), 788\u2013798 (2011). https:\/\/doi.org\/10.1109\/TASL.2010.2064307","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"2854_CR9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650","author":"B Desplanques","year":"2020","unstructured":"B. Desplanques, J. Thienpondt, K. Demuynck, ECAPA-TDNN: emphasized channel attention, propagation and aggregation in TDNN based speaker verification. Interspeech (2020). https:\/\/doi.org\/10.21437\/Interspeech.2020-2650","journal-title":"Interspeech"},{"issue":"16","key":"2854_CR10","doi-asserted-by":"publisher","first-page":"3447","DOI":"10.3390\/electronics12163447","volume":"12","author":"T Feng","year":"2023","unstructured":"T. Feng, H. Fan, F. Ge, S. Cao, C. Liang, Speaker recognition based on the joint loss function. Electronics 12(16), 3447 (2023). https:\/\/doi.org\/10.3390\/electronics12163447","journal-title":"Electronics"},{"issue":"8","key":"2854_CR11","doi-asserted-by":"publisher","first-page":"3471","DOI":"10.3390\/app14083471","volume":"14","author":"M Gao","year":"2024","unstructured":"M. Gao, X. Zhang, Improved convolutional neural network-time-delay neural network structure with repeated feature fusions for speaker verification. Appl. Sci. 14(8), 3471 (2024). https:\/\/doi.org\/10.3390\/app14083471","journal-title":"Appl. Sci."},{"key":"2854_CR12","doi-asserted-by":"crossref","unstructured":"H.-J. Heo, U.-H. Shin, R. Lee, Y. Cheon, H.-M. Park, NeXt-TDNN: modernizing multi-scale temporal convolution backbone for speaker verification. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing\u2013Proceedings (2024), p. 11186\u201311190,","DOI":"10.1109\/ICASSP48485.2024.10447037"},{"key":"2854_CR13","doi-asserted-by":"publisher","unstructured":"C.-L. Huang, Speaker characterization using TDNN, TDNN-LSTM, TDNN-LSTM-attention based speaker embeddings for NIST SRE 2019. Odyssey, the Speaker and Language Recognition Workshop (2020), p. 423\u2013427. https:\/\/doi.org\/10.21437\/ODYSSEY.2020-60","DOI":"10.21437\/ODYSSEY.2020-60"},{"key":"2854_CR14","doi-asserted-by":"crossref","unstructured":"W.T. Hutiri, A.Y. Ding, Bias in automated speaker recognition. Proceedings of ACM Conference on Fairness, Accountability, and Transparency (2022), p. 230\u2013247","DOI":"10.1145\/3531146.3533089"},{"key":"2854_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107232","volume":"127","author":"M Jakubec","year":"2024","unstructured":"M. Jakubec, R. Jarina, E. Lieskovska, P. Kasak, Deep speaker embeddings for speaker verification: review and experimental comparison. Eng. Appl. Artif. Intell. 127, 107232 (2024)","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"4","key":"2854_CR16","doi-asserted-by":"publisher","first-page":"1435","DOI":"10.1109\/TASL.2006.881693","volume":"15","author":"P Kenny","year":"2007","unstructured":"P. Kenny, G. Boulianne, P. Ouellet, P. Dumouchel, Joint factor analysis versus eigenchannels in speaker recognition. IEEE Trans. Audio Speech Lang. Process. 15(4), 1435\u20131447 (2007). https:\/\/doi.org\/10.1109\/TASL.2006.881693","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"2854_CR17","doi-asserted-by":"publisher","unstructured":"T. Ko, V. Peddinti, D. Povey, M. L. Seltzer, S. Khudanpur, A study on data augmentation of reverberant speech for robust speech recognition. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing\u2013Proceedings (2017), p. 5220\u20135224. https:\/\/doi.org\/10.1109\/ICASSP.2017.7953152","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"2854_CR18","doi-asserted-by":"publisher","first-page":"1385","DOI":"10.1109\/LSP.2021.3091932","volume":"28","author":"KA Lee","year":"2021","unstructured":"K.A. Lee, Q. Wang, T. Koshinaka, Xi-vector embedding for speaker recognition. IEEE Signal Process. Lett. 28, 1385\u20131389 (2021). https:\/\/doi.org\/10.1109\/LSP.2021.3091932","journal-title":"IEEE Signal Process. Lett."},{"key":"2854_CR19","doi-asserted-by":"publisher","unstructured":"Y. Lei, N. Scheffer, L. Ferrer, M. McLaren, A novel scheme for speaker recognition using a phonetically-aware deep neural network. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing\u2013Proceedings (2014), p. 1695\u20131699. https:\/\/doi.org\/10.1109\/ICASSP.2014.6853887","DOI":"10.1109\/ICASSP.2014.6853887"},{"key":"2854_CR20","doi-asserted-by":"publisher","unstructured":"C. Liao, J. Huang, H. Yuan, P. Yao, J. Tan, D. Zhang, F. Deng, X. Wang, C. Song, Dynamic TF-TDNN: dynamic time-delay neural network based on temporal-frequency attention for dialect recognition. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing\u2013Proceedings (2023), p. 1\u20135. https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10096335","DOI":"10.1109\/ICASSP49357.2023.10096335"},{"key":"2854_CR21","doi-asserted-by":"crossref","unstructured":"T. Liu, R.K. Das, K.A. Lee, H. Li, MFA: TDNN with multi-scale frequency-channel attention for text-independent speaker verification with short utterances. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing\u2013Proceedings (2022), p. 7517\u20137521","DOI":"10.1109\/ICASSP43922.2022.9747021"},{"issue":"7","key":"2854_CR22","doi-asserted-by":"publisher","first-page":"4233","DOI":"10.3390\/app13074233","volume":"13","author":"Q Luo","year":"2023","unstructured":"Q. Luo, R. Zhou, Multi-scale channel adaptive time-delay neural network and balanced fine-tuning for Arabic dialect identification. Appl. Sci. 13(7), 4233 (2023). https:\/\/doi.org\/10.3390\/app13074233","journal-title":"Appl. Sci."},{"key":"2854_CR23","doi-asserted-by":"publisher","unstructured":"P. Matejka, O. Glembek, O. Novotny, O. Plchot, F. Grezl, L. Burget, J.H. Cernocky, Analysis of DNN approaches to speaker identification. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing\u2013Proceedings (2016), p. 5100\u20135104. https:\/\/doi.org\/10.1109\/ICASSP.2016.7472649","DOI":"10.1109\/ICASSP.2016.7472649"},{"key":"2854_CR24","doi-asserted-by":"publisher","DOI":"10.21437\/INTERSPEECH.2016-1129","author":"M McLaren","year":"2016","unstructured":"M. McLaren, L. Ferrer, D. Castan, A. Lawson, The speakers in the wild (SITW) speaker recognition database. Interspeech (2016). https:\/\/doi.org\/10.21437\/INTERSPEECH.2016-1129","journal-title":"Interspeech"},{"key":"2854_CR25","doi-asserted-by":"publisher","DOI":"10.21437\/INTERSPEECH.2016-1137","author":"M McLaren","year":"2016","unstructured":"M. McLaren, L. Ferrer, D. Castan, A. Lawson, The 2016 speakers in the wild speaker recognition evaluation. Interspeech (2016). https:\/\/doi.org\/10.21437\/INTERSPEECH.2016-1137","journal-title":"Interspeech"},{"key":"2854_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/J.CSL.2019.101027","volume":"60","author":"A Nagrani","year":"2020","unstructured":"A. Nagrani, J.S. Chung, W. Xie, A. Zisserman, Voxceleb: large-scale speaker verification in the wild. Comput. Speech Lang. 60, 101027 (2020). https:\/\/doi.org\/10.1016\/J.CSL.2019.101027","journal-title":"Comput. Speech Lang."},{"key":"2854_CR27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950","author":"A Nagraniy","year":"2017","unstructured":"A. Nagraniy, J.S. Chungy, A. Zisserman, VoxCeleb: a large-scale speaker identification dataset. In Interspeech (2017). https:\/\/doi.org\/10.21437\/Interspeech.2017-950","journal-title":"In Interspeech"},{"key":"2854_CR28","doi-asserted-by":"publisher","unstructured":"S. Novoselov, A. Shulipa, I. Kremnev, A. Kozlov, V. Shchemelinin, On deep speaker embeddings for text-independent speaker recognition. Odyssey, The Speaker and Language Recognition Workshop (2018), p. 378\u2013385. https:\/\/doi.org\/10.21437\/ODYSSEY.2018-53","DOI":"10.21437\/ODYSSEY.2018-53"},{"key":"2854_CR29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2783","author":"S Novoselov","year":"2019","unstructured":"S. Novoselov, A. Gusev, A. Ivanov, T. Pekhovsky, A. Shulipa, G. Lavrentyeva, V. Volokhov, A. Kozlov, STC Speaker Recognition Systems for the VOiCES from a Distance Challenge. Interspeech (2019). https:\/\/doi.org\/10.21437\/Interspeech.2019-2783","journal-title":"Interspeech"},{"key":"2854_CR30","first-page":"2252","volume":"2018","author":"K Okabe","year":"2018","unstructured":"K. Okabe, T. Koshinaka, K. Shinoda, Attentive statistics pooling for deep speaker embedding. Interspeech 2018, 2252\u20132256 (2018)","journal-title":"Interspeech"},{"key":"2854_CR31","unstructured":"D. Povey, A. Ghoshal, G. Boulianne, L. Burget, O. Glembek, N. Goel, M. Hannemann, P. Motl\u00ed\u010dek, Y. Qian, P. Schwarz, J.S. Silovsky, G. Stemmer, K.V. Vesely, The Kaldi speech recognition Toolkit. IEEE Workshop on Automatic Speech Recognition and Understanding, Hilton Waikoloa Village, Big Island, Hawaii, US (2011). http:\/\/kaldi.sf.net\/"},{"key":"2854_CR32","unstructured":"D. Povey, X. Zhang, S. Khudanpur, Parallel training of DNNs with natural gradient and parameter averaging. 3rd International Conference on Learning Representations, ICLR\u2013Workshop Track Proceedings (2014)"},{"key":"2854_CR33","doi-asserted-by":"publisher","DOI":"10.21437\/INTERSPEECH.2018-1417","author":"D Povey","year":"2018","unstructured":"D. Povey, G. Cheng, Y. Wang, K. Li, H. Xu, M. Yarmohamadi, S. Khudanpur, Semi-orthogonal low-rank matrix factorization for deep neural networks. Interspeech (2018). https:\/\/doi.org\/10.21437\/INTERSPEECH.2018-1417","journal-title":"Interspeech"},{"issue":"1\u20133","key":"2854_CR34","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1006\/DSPR.1999.0361","volume":"10","author":"DA Reynolds","year":"2000","unstructured":"D.A. Reynolds, T.F. Quatieri, R.B. Dunn, Speaker verification using adapted Gaussian mixture models. Digit. Signal Process. 10(1\u20133), 19\u201341 (2000). https:\/\/doi.org\/10.1006\/DSPR.1999.0361","journal-title":"Digit. Signal Process."},{"issue":"10","key":"2854_CR35","doi-asserted-by":"publisher","first-page":"1671","DOI":"10.1109\/LSP.2015.2420092","volume":"22","author":"F Richardson","year":"2015","unstructured":"F. Richardson, D. Reynolds, N. Dehak, Deep neural network approaches to speaker and language recognition. IEEE Signal Process. Lett. 22(10), 1671\u20131675 (2015). https:\/\/doi.org\/10.1109\/LSP.2015.2420092","journal-title":"IEEE Signal Process. Lett."},{"key":"2854_CR36","doi-asserted-by":"publisher","DOI":"10.21437\/INTERSPEECH.2020-1446","author":"P Safari","year":"2020","unstructured":"P. Safari, M. India, J. Hernando, Self-attention encoding and pooling for speaker recognition. Interspeech (2020). https:\/\/doi.org\/10.21437\/INTERSPEECH.2020-1446","journal-title":"Interspeech"},{"issue":"3","key":"2854_CR37","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1007\/s10462-023-10688-w","volume":"57","author":"R Sharma","year":"2024","unstructured":"R. Sharma, D. Govind, J. Mishra, A. Dubey, K. Deepak, S. Prasanna, Milestones in speaker recognition. Artif. Intell. Rev. 57(3), 58 (2024)","journal-title":"Artif. Intell. Rev."},{"key":"2854_CR38","unstructured":"D. Snyder, G. Chen, D. Povey, MUSAN: a music, speech, and noise corpus (2015). arXiv preprint arXiv:1510.08484, http:\/\/www.itl.nist.gov\/iad\/mig\/tests\/sre\/"},{"key":"2854_CR39","doi-asserted-by":"publisher","unstructured":"D. Snyder, P. Ghahremani, D. Povey, D. Garcia-Romero, Y. Carmiel, S. Khudanpur, Deep neural network-based speaker embeddings for end-to-end speaker verification. SLT, IEEE Workshop on Spoken Language Technology\u2013Proceedings (2016), p. 165\u2013170. https:\/\/doi.org\/10.1109\/SLT.2016.7846260","DOI":"10.1109\/SLT.2016.7846260"},{"key":"2854_CR40","doi-asserted-by":"publisher","unstructured":"D. Snyder, D. Garcia-Romero, G. Sell, D. Povey, S. Khudanpur, X-vectors: robust DNN embeddings for speaker recognition. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing\u2013Proceedings (2018), p. 5329\u20135333. https:\/\/doi.org\/10.1109\/ICASSP.2018.8461375","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"2854_CR41","doi-asserted-by":"publisher","unstructured":"D. Snyder, D. Garcia-Romero, G. Sell, A. McCree, D. Povey, S. Khudanpur, Speaker recognition for multi-speaker conversations using X-vectors. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing\u2013Proceedings (2019), p. 5796\u20135800. https:\/\/doi.org\/10.1109\/ICASSP.2019.8683760","DOI":"10.1109\/ICASSP.2019.8683760"},{"key":"2854_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/J.CSL.2019.101026","volume":"60","author":"J Villalba","year":"2020","unstructured":"J. Villalba, N. Chen, D. Snyder, D. Garcia-Romero, A. McCree, G. Sell, J. Borgstrom, L.P. Garc\u00eda-Perera, F. Richardson, R. Dehak, P.A. Torres-Carrasquillo, N. Dehak, State-of-the-art speaker recognition with neural network embeddings in NIST SRE18 and speakers in the Wild evaluations. Comput. Speech Lang. 60, 101026 (2020). https:\/\/doi.org\/10.1016\/J.CSL.2019.101026","journal-title":"Comput. Speech Lang."},{"issue":"6","key":"2854_CR43","doi-asserted-by":"publisher","first-page":"2147","DOI":"10.3390\/s22062147","volume":"22","author":"M Wang","year":"2022","unstructured":"M. Wang, D. Feng, T. Su, M. Chen, Attention-based temporal-frequency aggregation for speaker verification. Sensors 22(6), 2147 (2022)","journal-title":"Sensors"},{"key":"2854_CR44","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/J.NEUCOM.2020.06.079","volume":"412","author":"Y Wu","year":"2020","unstructured":"Y. Wu, C. Guo, H. Gao, J. Xu, G. Bai, Dilated residual networks with multi-level attention for speaker verification. Neurocomputing 412, 177\u2013186 (2020). https:\/\/doi.org\/10.1016\/J.NEUCOM.2020.06.079","journal-title":"Neurocomputing"},{"key":"2854_CR45","doi-asserted-by":"publisher","DOI":"10.21437\/INTERSPEECH.2019-1746","author":"L You","year":"2019","unstructured":"L. You, W. Guo, L. Dai, J. Du, Deep neural network embeddings with gating mechanisms for text-independent speaker verification. Interspeech (2019). https:\/\/doi.org\/10.21437\/INTERSPEECH.2019-1746","journal-title":"Interspeech"},{"key":"2854_CR46","doi-asserted-by":"publisher","DOI":"10.21437\/INTERSPEECH.2020-1626","author":"R Zhang","year":"2020","unstructured":"R. Zhang, J. Wei, W. Lu, L. Wang, M. Liu, L. Zhang, J. Jin, J. Xu, ARET: aggregated residual extended time-delay neural networks for speaker verification. Interspeech (2020). https:\/\/doi.org\/10.21437\/INTERSPEECH.2020-1626","journal-title":"Interspeech"},{"issue":"22","key":"2854_CR47","doi-asserted-by":"publisher","first-page":"26497","DOI":"10.1007\/s10489-023-04953-2","volume":"53","author":"R Zhang","year":"2023","unstructured":"R. Zhang, J. Wei, X. Lu, W. Lu, D. Jin, L. Zhang, J. Xu, J. Dang, TMS: temporal multi-scale in time-delay neural network for speaker verification. Appl. Intell. 53(22), 26497\u201326517 (2023)","journal-title":"Appl. Intell."},{"key":"2854_CR48","doi-asserted-by":"publisher","first-page":"76","DOI":"10.21437\/Interspeech.2021-356","volume":"45","author":"Y-J Zhang","year":"2021","unstructured":"Y.-J. Zhang, Y.-W. Wang, C.-P. Chen, C.-L. Lu, B.-C. Chan, Improving time delay neural network based speaker recognition with convolutional block and feature aggregation methods. Interspeech 45, 76\u201380 (2021). https:\/\/doi.org\/10.21437\/Interspeech.2021-356","journal-title":"Interspeech"},{"key":"2854_CR49","doi-asserted-by":"crossref","unstructured":"Z. Zhao, Z. Li, W. Wang, P. Zhang, PCF: ECAPA-TDNN with progressive channel fusion for speaker verification. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing\u2013Proceedings (2023), p. 1\u20135","DOI":"10.1109\/ICASSP49357.2023.10095051"},{"key":"2854_CR50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2210","author":"H Zhu","year":"2021","unstructured":"H. Zhu, K.A. Lee, H. Li, Serialized multi-layer multi-head attention for neural speaker embedding. Interspeech (2021). https:\/\/doi.org\/10.21437\/Interspeech.2021-2210","journal-title":"Interspeech"},{"key":"2854_CR51","first-page":"3573","volume":"2018","author":"Y Zhu","year":"2018","unstructured":"Y. Zhu, T. Ko, D. Snyder, B. Mak, D. Povey, Self-attentive speaker embeddings for text-independent speaker verification. Interspeech 2018, 3573\u20133577 (2018)","journal-title":"Interspeech"},{"key":"2854_CR52","doi-asserted-by":"publisher","first-page":"3573","DOI":"10.21437\/Interspeech.2018-1158","volume":"45","author":"Y Zhu","year":"2018","unstructured":"Y. Zhu, T. Ko, D. Snyder, B. Mak, D. Povey, Self-attentive speaker embeddings for text-independent speaker verification. Interspeech 45, 3573\u20133577 (2018). https:\/\/doi.org\/10.21437\/Interspeech.2018-1158","journal-title":"Interspeech"}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-024-02854-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00034-024-02854-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-024-02854-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T13:33:27Z","timestamp":1737380007000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00034-024-02854-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,19]]},"references-count":52,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["2854"],"URL":"https:\/\/doi.org\/10.1007\/s00034-024-02854-4","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"value":"0278-081X","type":"print"},{"value":"1531-5878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,19]]},"assertion":[{"value":"19 February 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 August 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 August 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 September 2024","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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval and Consent to Participate"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Human and Animal Ethics"}}]}}