{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:25:39Z","timestamp":1740122739745,"version":"3.37.3"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,5,21]],"date-time":"2022-05-21T00:00:00Z","timestamp":1653091200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,5,21]],"date-time":"2022-05-21T00:00:00Z","timestamp":1653091200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1007\/s10772-022-09973-w","type":"journal-article","created":{"date-parts":[[2022,5,21]],"date-time":"2022-05-21T14:02:39Z","timestamp":1653141759000},"page":"493-498","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A method of multi-models fusion for speaker recognition"],"prefix":"10.1007","volume":"25","author":[{"given":"Hao","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7059-9096","authenticated-orcid":false,"given":"Linkai","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Wen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,5,21]]},"reference":[{"key":"9973_CR1","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., & Sivic, J. (2016). Netvlad: Cnn architecture for weakly supervised place recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 5297\u20135307).","DOI":"10.1109\/CVPR.2016.572"},{"key":"9973_CR2","doi-asserted-by":"crossref","unstructured":"Cai, W., Chen, J., & Li, M. (2018). Exploring the encoding layer and loss function in end-to-end speaker and language recognition system. In Proc. Odyssey 2018 The Speaker and Language Recognition Workshop (pp. 74\u201381).","DOI":"10.21437\/Odyssey.2018-11"},{"key":"9973_CR3","doi-asserted-by":"crossref","unstructured":"Chung, J. S.,\u00a0 Nagrani, A., & Zisserman, A. (2018). Voxceleb2: Deep speaker recognition. Proceedings of Interspeech, 2018, 1086\u20131090.","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"9973_CR4","doi-asserted-by":"crossref","unstructured":"Dai, M., Dai, G., Wu, Y., Xia, Y., Shen, F., & Zhang, H. (2019). An improved feature fusion for speaker recognition. In 2019 IEEE Fourth International Conference on Data Science in Cyberspace (DSC) (pp. 183\u2013187). IEEE.","DOI":"10.1109\/DSC.2019.00035"},{"issue":"4","key":"9973_CR5","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2010","unstructured":"Dehak, N., Kenny, P. J., Dehak, R., Dumouchel, P., & Ouellet, P. (2010). Front-end factor analysis for speaker verification. IEEE Transactions on Audio, Speech, and Language Processing, 19(4), 788\u2013798.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9973_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., & Zafeiriou, S. (2019). Arcface: Additive angular margin loss for deep face recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 4690\u20134699).","DOI":"10.1109\/CVPR.2019.00482"},{"key":"9973_CR7","first-page":"2019","volume":"2878\u20132882","author":"A Hajavi","year":"2019","unstructured":"Hajavi, A., & Etemad, A. (2019). A deep neural network for short-segment speaker recognition. Proceedings of Interspeech, 2878\u20132882, 2019.","journal-title":"Proceedings of Interspeech"},{"key":"9973_CR8","unstructured":"Hajibabaei, M., & Dai, D. (2018). Unified hypersphere embedding for speaker recognition. arXiv preprint arXiv:1807.08312."},{"key":"9973_CR9","doi-asserted-by":"crossref","unstructured":"Ioffe, S. (2006). Probabilistic linear discriminant analysis. In European Conference on Computer Vision (pp. 531\u2013542). Springer.","DOI":"10.1007\/11744085_41"},{"key":"9973_CR10","doi-asserted-by":"crossref","unstructured":"Nagrani, A., Chung, J. S., & Zisserman, A. (2017). Voxceleb: A large-scale speaker identification dataset. Proc. Interspeech 2017 (pp. 2616\u20132620).","DOI":"10.21437\/Interspeech.2017-950"},{"issue":"10","key":"9973_CR11","first-page":"2839","volume":"38","author":"S Nian","year":"2018","unstructured":"Nian, S., Yi, Z., Haibo, L., & Chao, H. (2018). Short utterance speaker recognition algorithm based on multi-featured i-vector. Journal of Computer Applications, 38(10), 2839.","journal-title":"Journal of Computer Applications"},{"key":"9973_CR12","doi-asserted-by":"crossref","unstructured":"Ramou, N., Djeddou, M., & Guerti, M. (2011). Two classifiers score fusion for text independent speaker verification. In 2011 11th International Conference on Intelligent Systems Design and Applications (pp. 937\u2013940). IEEE.","DOI":"10.1109\/ISDA.2011.6121778"},{"key":"9973_CR13","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., & Philbin, J. (2015). Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 815\u2013823).","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"9973_CR14","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. Computerence."},{"key":"9973_CR15","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., & Povey, D. (2015). Time delay deep neural network-based universal background models for speaker recognition. In 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) (pp. 92\u201397). IEEE.","DOI":"10.1109\/ASRU.2015.7404779"},{"key":"9973_CR16","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Povey, D., & Khudanpur, S. (2017). Deep neural network embeddings for text-independent speaker verification. In Interspeech (pp. 999\u20131003).","DOI":"10.21437\/Interspeech.2017-620"},{"key":"9973_CR17","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Sell, G., Povey, D., & Khudanpur, S. (2018). X-vectors: Robust dnn embeddings for speaker recognition. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 5329\u20135333). IEEE.","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"9973_CR18","doi-asserted-by":"crossref","unstructured":"Variani, E., Lei, X., & McDermott, E. (2014). Ignacio\u00a0Lopez Moreno, and Javier Gonzalez-Dominguez. Deep neural networks for small footprint text-dependent speaker verification. In 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 4052\u20134056). IEEE","DOI":"10.1109\/ICASSP.2014.6854363"},{"issue":"7","key":"9973_CR20","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., & Liu, H. (2018). Additive margin softmax for face verification. IEEE Signal Processing Letters, 25(7), 926\u2013930.","journal-title":"IEEE Signal Processing Letters"},{"key":"9973_CR19","doi-asserted-by":"crossref","unstructured":"Wang, Z., Yao, K., Li, X., & Fang, S. (2020). Multi-resolution multi-head attention in deep speaker embedding. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 6464\u20136468). IEEE.","DOI":"10.1109\/ICASSP40776.2020.9053217"},{"key":"9973_CR21","doi-asserted-by":"crossref","unstructured":"Xie, W., Nagrani, A., Chung, J. S., & Zisserman, A. (2019). Utterance-level aggregation for speaker recognition in the wild. In ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 5791\u20135795). IEEE.","DOI":"10.1109\/ICASSP.2019.8683120"},{"key":"9973_CR22","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Arandjelovi\u0107, R., & Zisserman, A. (2018). Ghostvlad for set-based face recognition. In Asian Conference on Computer Vision (pp. 35\u201350). Springer.","DOI":"10.1007\/978-3-030-20890-5_3"},{"key":"9973_CR23","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Ko, T., Snyder, D., Mak, B., & Povey, D. (2018). Self-attentive speaker embeddings for text-independent speaker verification. In Interspeech (pp. 3573\u20133577).","DOI":"10.21437\/Interspeech.2018-1158"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-022-09973-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-022-09973-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-022-09973-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,21]],"date-time":"2022-06-21T11:45:14Z","timestamp":1655811914000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-022-09973-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,21]]},"references-count":23,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["9973"],"URL":"https:\/\/doi.org\/10.1007\/s10772-022-09973-w","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2022,5,21]]},"assertion":[{"value":"7 December 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 May 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}