{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T07:58:00Z","timestamp":1742975880513,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031428227"},{"type":"electronic","value":"9783031428234"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-42823-4_20","type":"book-chapter","created":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T23:04:42Z","timestamp":1694732682000},"page":"270-282","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Novel Self-supervised Representation Learning Model for\u00a0an\u00a0Open-Set Speaker Recognition"],"prefix":"10.1007","author":[{"given":"Abu Quwsar","family":"Ohi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marina L.","family":"Gavrilova","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,15]]},"reference":[{"key":"20_CR1","unstructured":"Bromley, J., Guyon, I., LeCun, Y., S\u00e4ckinger, E., Shah, R.: Signature verification using a Siamese time delay neural network. In: Proceedings of the 6th International Conference on Neural Information Processing Systems, pp. 737\u2013744 (1993)"},{"key":"20_CR2","first-page":"9912","volume":"33","author":"M Caron","year":"2020","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. Adv. Neural. Inf. Process. Syst. 33, 9912\u20139924 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR3","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple Siamese representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15750\u201315758 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Chung, J.S., et al.: In defence of metric learning for speaker recognition. In: Proc. Interspeech 2020, pp. 2977\u20132981 (2020)","DOI":"10.21437\/Interspeech.2020-1064"},{"issue":"4","key":"20_CR6","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.: Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 19(4), 788\u2013798 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"20_CR7","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.neunet.2017.12.012","volume":"107","author":"S Elfwing","year":"2018","unstructured":"Elfwing, S., Uchibe, E., Doya, K.: Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural Netw. 107, 3\u201311 (2018)","journal-title":"Neural Netw."},{"key":"20_CR8","first-page":"21271","volume":"33","author":"JB Grill","year":"2020","unstructured":"Grill, J.B., et al.: Bootstrap your own latent-a new approach to self-supervised learning. Adv. Neural. Inf. Process. Syst. 33, 21271\u201321284 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Jung, J.w., Kim, Y.J., Heo, H.S., Lee, B.J., Kwon, Y., Chung, J.S.: Pushing the limits of raw waveform speaker recognition. arXiv preprint 2203 (2022)","DOI":"10.21437\/Interspeech.2022-126"},{"issue":"6","key":"20_CR11","doi-asserted-by":"publisher","first-page":"1253","DOI":"10.1109\/JSTSP.2022.3200915","volume":"16","author":"J Kang","year":"2022","unstructured":"Kang, J., Huh, J., Heo, H.S., Chung, J.S.: Augmentation adversarial training for self-supervised speaker representation learning. IEEE J. Sel. Top. Signal Process. 16(6), 1253\u20131262 (2022)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"20_CR12","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/978-981-13-8969-6_5","volume":"10","author":"A Ku\u015bmierczyk","year":"2020","unstructured":"Ku\u015bmierczyk, A., S\u0142awi\u0144ska, M., \u017baba, K., Saeed, K.: Biometric fusion system using face and voice recognition: a comparison approach: biometric fusion system using face and voice characteristics. Adv. Comput. Syst. Secur. 10, 71\u201389 (2020)","journal-title":"Adv. Comput. Syst. Secur."},{"issue":"11","key":"20_CR13","doi-asserted-by":"publisher","first-page":"631","DOI":"10.3390\/e19110631","volume":"19","author":"TO Kv\u00e5lseth","year":"2017","unstructured":"Kv\u00e5lseth, T.O.: On normalized mutual information: measure derivations and properties. Entropy 19(11), 631 (2017)","journal-title":"Entropy"},{"key":"20_CR14","unstructured":"Li, C., et al.: Deep speaker: an end-to-end neural speaker embedding system. arXiv preprint arXiv:1705.02304 (2017)"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"20_CR16","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"20_CR17","unstructured":"Mun, S.H., Kang, W.H., Han, M.H., Kim, N.S.: Unsupervised representation learning for speaker recognition via contrastive equilibrium learning. arXiv preprint arXiv:2010.11433 (2020)"},{"key":"20_CR18","first-page":"33","volume":"3","author":"A Nagrani","year":"2017","unstructured":"Nagrani, A., Chung, J.S., Zisserman, A.: VoxCeleb: a large-scale speaker identification dataset. Telephony 3, 33\u2013039 (2017)","journal-title":"Telephony"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Panayotov, V., Chen, G., Povey, D., Khudanpur, S.: LibriSpeech: an ASR corpus based on public domain audio books. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5206\u20135210. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Saeed, K.: New Directions in Behavioral Biometrics. CRC Press, Boca Raton (2016)","DOI":"10.1201\/9781315366760"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Sang, M., Li, H., Liu, F., Arnold, A.O., Wan, L.: Self-supervised speaker verification with simple Siamese network and self-supervised regularization. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6127\u20136131. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9747526"},{"key":"20_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1007\/978-3-642-04277-5_18","volume-title":"Artificial Neural Networks \u2013 ICANN 2009","author":"JM Santos","year":"2009","unstructured":"Santos, J.M., Embrechts, M.: On the use of the adjusted rand index as a metric for evaluating supervised classification. In: Alippi, C., Polycarpou, M., Panayiotou, C., Ellinas, G. (eds.) ICANN 2009, Part II. LNCS, vol. 5769, pp. 175\u2013184. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-04277-5_18"},{"key":"20_CR23","unstructured":"Snyder, D., Chen, G., Povey, D.: MUSAN: a music, speech, and noise corpus. arXiv preprint arXiv:1510.08484 (2015)"},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Povey, D., Khudanpur, S.: Deep neural network embeddings for text-independent speaker verification. In: Interspeech, vol. 2017, pp. 999\u20131003 (2017)","DOI":"10.21437\/Interspeech.2017-620"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Tanveer, M.I., Casabuena, D., Karlgren, J., Jones, R.: Unsupervised speaker diarization that is agnostic to language, overlap-aware, and tuning free. In: Proceedings of the Interspeech 2022, pp. 1481\u20131485 (2022)","DOI":"10.21437\/Interspeech.2022-10605"},{"key":"20_CR26","doi-asserted-by":"crossref","unstructured":"Tao, R., Lee, K.A., Das, R.K., Hautam\u00e4ki, V., Li, H.: Self-supervised speaker recognition with loss-gated learning. In: ICASSP IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6142\u20136146. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9747162"},{"key":"20_CR27","unstructured":"Ulyanov, D., Vedaldi, A., Lempitsky, V.: Instance normalization: the missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022 (2016)"},{"key":"20_CR28","unstructured":"Yanushkevich, S.N., Stoica, A., Srihari, S.N., Shmerko, V.P., Gavrilova, M.: Simulation of biometric information: the new generation of biometric systems. In: Modeling and Simulation in Biometric Technology, pp. 87\u201398 (2004)"}],"container-title":["Lecture Notes in Computer Science","Computer Information Systems and Industrial Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-42823-4_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T23:07:58Z","timestamp":1694732878000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-42823-4_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031428227","9783031428234"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-42823-4_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"15 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CISIM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Information Systems and Industrial Management","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tokyo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cisim2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cisim2023.wi.pb.edu.pl\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"MS CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"77","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"36","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"47% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}