{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:27:27Z","timestamp":1740122847252,"version":"3.37.3"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62071302"],"award-info":[{"award-number":["62071302"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s10772-023-10051-y","type":"journal-article","created":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T15:47:42Z","timestamp":1698853662000},"page":"851-857","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CI-Mix: cut instance mix for robust speaker verification"],"prefix":"10.1007","volume":"26","author":[{"given":"Yibo","family":"Duan","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0924-408X","authenticated-orcid":false,"given":"Yanhua","family":"Long","sequence":"additional","affiliation":[]},{"given":"Yijie","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,1]]},"reference":[{"issue":"2","key":"10051_CR1","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.neunet.2021.03.004","volume":"140","author":"Z Bai","year":"2021","unstructured":"Bai, Z., & Zhang, X. L. (2021). Speaker recognition based on deep learning: An overview. Neural Networks, 140(2), 65\u201399.","journal-title":"Neural Networks"},{"doi-asserted-by":"crossref","unstructured":"Brown, A., Huh, J., Nagrani, A., Chung, J. S., & Zisserman, A. (2021). Playing a part: Speaker verification at the movies. In IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 6174\u20136178).","key":"10051_CR2","DOI":"10.1109\/ICASSP39728.2021.9413815"},{"doi-asserted-by":"crossref","unstructured":"Chung, J. S., Nagrani, A., & Zisserman, A. (2018). VoxCeleb2: Deep speaker recognition. In The 19th international speech communication association (INTERSPEECH) (pp. 1086\u20131090).","key":"10051_CR3","DOI":"10.21437\/Interspeech.2018-1929"},{"doi-asserted-by":"crossref","unstructured":"Desplanques, B., Thienpondt, J., & Demuynck, K. (2020). ECAPA-TDNN: Emphasized channel attention, propagation and aggregation in TDNN based speaker verification. In The 21th international speech communication association (INTERSPEECH) (pp. 3830\u20133834).","key":"10051_CR4","DOI":"10.21437\/Interspeech.2020-2650"},{"doi-asserted-by":"crossref","unstructured":"Fan, Y., Kang, J. W., Li, L. T., Li, K. C., Chen, H. L., Cheng, S. T., Zhang, P. Y., Zhou, Z. Y., Cai, Y. Q., & Wang, D. (2020). CN-Celeb: A challenging Chinese speaker recognition dataset. IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 7604\u20137608).","key":"10051_CR5","DOI":"10.1109\/ICASSP40776.2020.9054017"},{"doi-asserted-by":"crossref","unstructured":"Fonseca, E., Plakal, M., Ellis, D. P., Font, F., Favory, X., & Serra, X. (2019). Learning sound event classifiers from web audio with noisy labels. In IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 21\u201325).","key":"10051_CR6","DOI":"10.1109\/ICASSP.2019.8683158"},{"doi-asserted-by":"crossref","unstructured":"Han, S., Byun, J., & Shin, J. W. (2021). Time-domain speaker verification using temporal convolutional networks. In IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 6688\u20136692).","key":"10051_CR7","DOI":"10.1109\/ICASSP39728.2021.9414765"},{"issue":"6","key":"10051_CR8","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1109\/MSP.2015.2462851","volume":"32","author":"JHL Hansen","year":"2015","unstructured":"Hansen, J. H. L., & Hasan, T. (2015). Speaker recognition by machines and humans: A tutorial review. IEEE Signal Processing Magazine, 32(6), 74\u201399.","journal-title":"IEEE Signal Processing Magazine"},{"doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 7132\u20137141).","key":"10051_CR9","DOI":"10.1109\/CVPR.2018.00745"},{"doi-asserted-by":"crossref","unstructured":"Hu, H. R., Song, Y., Liu, Y., Dai, L. R., McLoughlin, I., & Liu, L. (2022). Domain robust deep embedding learning for speaker recognition. In IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 7182\u20137186).","key":"10051_CR10","DOI":"10.1109\/ICASSP43922.2022.9747364"},{"doi-asserted-by":"crossref","unstructured":"Jain, A., Samala, P. R., Mittal, D., Jyothi, P., & Singh, M. (2022). SPLICEOUT: A simple and efficient audio augmentation method. In Interspeech (pp. 2678\u20132682).","key":"10051_CR11","DOI":"10.21437\/Interspeech.2022-572"},{"doi-asserted-by":"crossref","unstructured":"Kataria, S., Villalba, J., Moro-Vel\u00e1zquez, L., & Dehak, N. (2022). Joint domain adaptation and speech bandwidth extension using time-domain GANs for speaker verification. In Interspeech (pp. 615\u2013619).","key":"10051_CR12","DOI":"10.21437\/Interspeech.2022-10900"},{"unstructured":"Kingma, D., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv:1412.6980 [cs.LG]","key":"10051_CR13"},{"doi-asserted-by":"crossref","unstructured":"Ko, T., Peddinti, V., Povey, D., Seltzer, M. L., & Khudanpur, S. (2017). A study on data augmentation of reverberant speech for robust speech recognition. In IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 5220\u20135224).","key":"10051_CR14","DOI":"10.1109\/ICASSP.2017.7953152"},{"doi-asserted-by":"crossref","unstructured":"Li, J., Han, J., & Song, H. (2021). Gradient regularization for noise-robust speaker verification. In Interspeech (pp. 1074\u20131078).","key":"10051_CR15","DOI":"10.21437\/Interspeech.2021-1216"},{"doi-asserted-by":"crossref","unstructured":"Lin, W., & Mak, M. W. (2022). Robust speaker verification using population-based data augmentation. In IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 7642\u20137646).","key":"10051_CR16","DOI":"10.1109\/ICASSP43922.2022.9746956"},{"doi-asserted-by":"crossref","unstructured":"Liu, X., Sahidullah, M., & Kinnunen, T. (2022). Learnable nonlinear compression for robust speaker verification. In IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 7962\u20137966).","key":"10051_CR17","DOI":"10.1109\/ICASSP43922.2022.9747185"},{"doi-asserted-by":"crossref","unstructured":"Meng, L., Xu, J., Tan, X., Wang, J., Qin, T., & Xu, B. (2021). MixSpeech: Data augmentation for low-resource automatic speech recognition. In IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 7008\u20137012).","key":"10051_CR18","DOI":"10.1109\/ICASSP39728.2021.9414483"},{"doi-asserted-by":"crossref","unstructured":"Park, D. S., Chan, W., Zhang, Y., Chiu, C. C., Zoph, B., Cubuk, E. D., & Le, Q. V. (2019). SpecAugment: A simple data augmentation method for automatic speech recognition. In The 20th international speech communication association (INTERSPEECH) (pp. 2613\u20132617).","key":"10051_CR19","DOI":"10.21437\/Interspeech.2019-2680"},{"unstructured":"Snyder, D., Chen, G., & Povey, D. (2015). MUSAN: A music, speech, and noise corpus, arxiv:1510.08484","key":"10051_CR20"},{"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 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 5329\u20135333).","key":"10051_CR21","DOI":"10.1109\/ICASSP.2018.8461375"},{"unstructured":"Thienpondt, J., Desplanques, B., & Demuynck, K. (2021). The IDLAB VoxCeleb speaker recognition challenge 2021 system description.","key":"10051_CR22"},{"key":"10051_CR23","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, 926\u2013930.","journal-title":"IEEE Signal Processing Letters"},{"doi-asserted-by":"crossref","unstructured":"Wang, S., Rohdin, J., Plchot, O., Burget, L., Yu, K., & \u010cernock\u00fd, J. (2020). Investigation of specaugment for deep speaker embedding learning. In IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 7139\u20137143).","key":"10051_CR24","DOI":"10.1109\/ICASSP40776.2020.9053481"},{"doi-asserted-by":"crossref","unstructured":"Wu, H., Li, X., Liu, A. T., Wu, Z., Meng, H., & Lee, H.-Y. (2021). Adversarial defense for automatic speaker verification by cascaded self-supervised learning models. In IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 6718\u20136722).","key":"10051_CR25","DOI":"10.1109\/ICASSP39728.2021.9413737"},{"unstructured":"Wu, S., Zhang, H., Valiant, G., & R\u00e9, C. (2020). On the generalization effects of linear transformations in data augmentation. In International conference on machine learning (ICML).","key":"10051_CR26"},{"unstructured":"Wu, S., Zhang, H. R., Valiant, G., & R\u2019e, C. (2020). On the generalization effects of linear transformations in data augmentation. In International conference on machine learning (ICML).","key":"10051_CR27"},{"doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S. J., Chun, S., Choe, J., & Yoo, Y. (2019). CutMix: Regularization strategy to train strong classifiers with localizable features. In IEEE\/CVF international conference on computer vision (ICCV) (pp. 6022\u20136031).","key":"10051_CR28","DOI":"10.1109\/ICCV.2019.00612"},{"unstructured":"Zhang, H., Cisse, M., Dauphin, Y. N., & Lopez-Paz, D. (2018). Mixup: Beyond empirical risk minimization. In International conference on learning representations (ICLR).","key":"10051_CR29"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-023-10051-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-023-10051-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-023-10051-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T10:12:03Z","timestamp":1704967923000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-023-10051-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,1]]},"references-count":29,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["10051"],"URL":"https:\/\/doi.org\/10.1007\/s10772-023-10051-y","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2023,11,1]]},"assertion":[{"value":"23 May 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 September 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 November 2023","order":3,"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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}