{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T15:38:44Z","timestamp":1784129924428,"version":"3.55.0"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031712524","type":"print"},{"value":"9783031712531","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T00:00:00Z","timestamp":1727568000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T00:00:00Z","timestamp":1727568000000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-71253-1_21","type":"book-chapter","created":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T12:01:49Z","timestamp":1727524909000},"page":"286-297","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["SC-EcapaTdnn: ECAPA-TDNN with Separable Convolutional for Speaker Recognition"],"prefix":"10.1007","author":[{"given":"Erhua","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenmin","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,29]]},"reference":[{"key":"21_CR1","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2011","unstructured":"Dehak, N., Kenny, P., Dehak, R., Dumouchel, P., Ouellet, P.: Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 19, 788\u2013798 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"21_CR2","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1006\/dspr.1999.0361","volume":"10","author":"D Reynolds","year":"2000","unstructured":"Reynolds, D., Quatieri, T., Dunn, R.: Speaker recognition using adapted Gaussian mixture models. Digit. Signal Process. 10, 19\u201341 (2000)","journal-title":"Digit. Signal Process."},{"key":"21_CR3","doi-asserted-by":"publisher","unstructured":"Ioffe, S.: Probabilistic linear discriminant analysis. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, pp. 531\u2013542. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11744085_41","DOI":"10.1007\/11744085_41"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Sell, G., Povey, D., Khudanpur, S.: X-vectors: robust DNN embeddings for speaker recognition. In: Proceedings of the Interspeech, pp. 532\u2013536 (2018)","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"He, K., et al.: Deep residual learning for image verification. In: IEEE Conference on Computer Vision and Pattern Verification (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Zhou, T., Zhao, Y., Wu, J.: ResNeXt and Res2Net structures for speaker recognition. In: 2021 IEEE Spoken Language Technology Workshop (SLT), pp. 301\u2013307. IEEE (2021)","DOI":"10.1109\/SLT48900.2021.9383531"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Liu, B., et al.: DF-ResNet: boosting speaker recognition performance with depth-first design. In: INTERSPEECH, pp. 296\u2013300 (2022)","DOI":"10.21437\/Interspeech.2022-484"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Jin, C., He, B.C., Hui K, et al. TDNN: a two-stage deep neural network for prompt-independent automated essay scoring. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1088\u20131097 (2018)","DOI":"10.18653\/v1\/P18-1100"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Desplanques, B., Thienpondt, J., Demuynck, K.: ECAPA-TDNN: emphasized channel attention, propagation and aggregation in TDNN based speaker veri-fication. arxiv preprint arXiv:2005.07143 (2020)","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"21_CR10","unstructured":"Thienpondt, J., Desplanques, B., Demuynck, K.: The IDLAB voxceleb speaker recognition challenge 2020 system description. arxiv preprint arxiv:2010.12468 (2020)"},{"key":"21_CR11","unstructured":"Changpinyo, S., Sandler, M., Zhmoginov, A.: The power of sparsity in convolutional neural networks. arxiv preprint arxiv:1702.06257 (2017)"},{"key":"21_CR12","unstructured":"Dong, X., Yang, Y.: Network pruning via transformable architecture search. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: ECA-Net: efficient channel attention for deep convolutional neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Verification (2020)","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: CAM++: a fast and efficient network for speaker recognition using context-aware masking. arxiv preprint arxiv:2303.00332 (2023)","DOI":"10.21437\/Interspeech.2023-1513"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Yu, Y.-Q., Li, W.-J.: Densely connected time delay neural network for speaker recognition. In: INTERSPEECH (2020)","DOI":"10.21437\/Interspeech.2020-1275"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Zhao, Z., et al.: PCF: ECAPA-TDNN with progressive channel fusion for speaker recognition. In: ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2023)","DOI":"10.1109\/ICASSP49357.2023.10095051"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Zhong, X., et al.: Squeeze-and-excitation wide residual networks in image classification. In: 2019 IEEE International Conference on Image Processing (ICIP). IEEE (2019)","DOI":"10.1109\/ICIP.2019.8803000"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Bu, H., et al.: AISHELL-1: an open-source mandarin speech corpus and a speech verification baseline. In: 2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I\/O Systems and Assessment (O-COCOSDA). IEEE (2017)","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"21_CR19","unstructured":"Du, J., et al.: AISHELL-2: Transforming mandarin ASR research into industrial scale. arXiv preprint arXiv:1808.10583 (2018)"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Li, L., et al.: CN-Celeb: multi-genre speaker recognition. Speech Commun. (2022)","DOI":"10.1016\/j.specom.2022.01.002"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: Arc-face: additive angular margin loss for deep face verification. In: IEEE Conference on Computer Vision and Pattern Verification (CVPR), pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"21_CR22","unstructured":"Shum, S., et al.: Unsupervised speaker adaptation based on the cosine similarity for text-independent speaker recognition. Odyssey (2010)"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: Deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"21_CR24","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv:1412.6980 (2014)"},{"key":"21_CR25","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008)"}],"container-title":["IFIP Advances in Information and Communication Technology","Intelligence Science V"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-71253-1_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T12:03:54Z","timestamp":1727525034000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-71253-1_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,29]]},"ISBN":["9783031712524","9783031712531"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-71253-1_21","relation":{},"ISSN":["1868-4238","1868-422X"],"issn-type":[{"value":"1868-4238","type":"print"},{"value":"1868-422X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,29]]},"assertion":[{"value":"29 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligence Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nanjing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icis2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cs.njust.edu.cn\/icis2024\/main.psp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}