{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,12]],"date-time":"2024-09-12T00:18:35Z","timestamp":1726100315958},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030602758"},{"type":"electronic","value":"9783030602765"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-60276-5_44","type":"book-chapter","created":{"date-parts":[[2020,10,4]],"date-time":"2020-10-04T07:02:44Z","timestamp":1601794964000},"page":"457-466","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Score Normalization of X-Vector Speaker Verification System for Short-Duration Speaker Verification Challenge"],"prefix":"10.1007","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-8799-601X","authenticated-orcid":false,"given":"Ivan","family":"Rakhmanenko","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0001-8000-2716","authenticated-orcid":false,"given":"Evgeny","family":"Kostyuchenko","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-3651-0665","authenticated-orcid":false,"given":"Evgeny","family":"Choynzonov","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-2606-661X","authenticated-orcid":false,"given":"Lidiya","family":"Balatskaya","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-2393-6701","authenticated-orcid":false,"given":"Alexander","family":"Shelupanov","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,9,29]]},"reference":[{"key":"44_CR1","unstructured":"Zeinali, H., Lee, K.A., Alam, J., Burget L.: Short-duration Speaker Verification (SdSV) Challenge 2020: The Challenge Evaluation Plan. arXiv preprint https:\/\/arxiv.org\/abs\/1912.06311 (2019)"},{"key":"44_CR2","doi-asserted-by":"crossref","unstructured":"Jung, J.W., Heo, H.S., Kim, J.H., Shim, H.J., Yu, H.J.: RawNet: advanced end-to-end deep neural network using raw waveforms for text-independent speaker verification. In: Proceedings Interspeech 2019, pp. 1268\u20131272 (2019)","DOI":"10.21437\/Interspeech.2019-1982"},{"key":"44_CR3","doi-asserted-by":"crossref","unstructured":"Yun, S., Cho, J., Eum, J., Chang, W., Hwang, K.: An end-to-end text-independent speaker verification framework with a keyword adversarial network. In: Proceedings Interspeech 2019, pp. 2923\u20132927 (2019)","DOI":"10.21437\/Interspeech.2019-2208"},{"key":"44_CR4","unstructured":"Li, C., et al.: Deep speaker: an end-to-end neural speaker embedding system. arXiv preprint https:\/\/arxiv.org\/abs\/1705.02304 (2017)"},{"key":"44_CR5","doi-asserted-by":"crossref","unstructured":"Xie, W., Nagrani, A., Chung, J.S., Zisserman, A.: Utterance-level aggregation for speaker recognition in the wild. In: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5791\u20135795. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683120"},{"issue":"4","key":"44_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":"44_CR7","doi-asserted-by":"crossref","unstructured":"Rohdin, J., et al.: End-to-end DNN based speaker recognition inspired by i-vector and PLDA. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4874\u20134878 (2018)","DOI":"10.1109\/ICASSP.2018.8461958"},{"key":"44_CR8","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Sell, G., Povey, D., Khudanpur, S.: X-vectors: rRobust DNN embeddings for speaker recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5329\u20135333 (2018)","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"44_CR9","doi-asserted-by":"crossref","unstructured":"Prince, S.J., Elder, J.H.: Probabilistic linear discriminant analysis for inferences about identity. In: 2007 IEEE 11th International Conference on Computer Vision, pp. 1\u20138 (2007)","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"44_CR10","doi-asserted-by":"crossref","unstructured":"Garcia-Romero, D., et al.: X-vector DNN refinement with full-length recordings for speaker recognition. In: Proceedings Interspeech 2019, pp. 1493\u20131496 (2019)","DOI":"10.21437\/Interspeech.2019-2205"},{"key":"44_CR11","doi-asserted-by":"crossref","unstructured":"Ramoji, S., Krishnan, P., Ganapathy, S.: NPLDA: a deep neural PLDA model for speaker verification. In: Proceedings Odyssey 2020 The Speaker and Language Recognition Workshop, pp. 202\u2013209 (2020)","DOI":"10.21437\/Odyssey.2020-29"},{"key":"44_CR12","unstructured":"Povey, D., Ghoshal, A., Boulianne, G., et al.: The Kaldi speech recognition toolkit. In: IEEE 2011 Workshop on Automatic Speech Recognition and Understanding. IEEE Signal Processing Society (2011)"},{"key":"44_CR13","doi-asserted-by":"crossref","unstructured":"Snyder, D., et al.: Speaker recognition for multi-speaker conversations using x-vectors. In: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5796\u20135800. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683760"},{"key":"44_CR14","doi-asserted-by":"crossref","unstructured":"Barras, C., Gauvain, J.L.: Feature and score normalization for speaker verification of cellular data. In: 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2003, vol. 2, pp. 49\u201352. IEEE (2003)","DOI":"10.1109\/ICASSP.2003.1202291"},{"key":"44_CR15","doi-asserted-by":"crossref","unstructured":"Nagrani, A., Chung, J.S., Zisserman, A.: VoxCeleb: a large-scale speaker identification dataset. arXiv preprint https:\/\/arxiv.org\/abs\/1706.08612 (2017)","DOI":"10.21437\/Interspeech.2017-950"},{"key":"44_CR16","doi-asserted-by":"crossref","unstructured":"Zeinali, H., Burget, L., \u010cernock\u00fd, J.: A multi purpose and large scale speech corpus in Persian and English for speaker and speech recognition: the DeepMine database. arXiv preprint https:\/\/arxiv.org\/abs\/1912.03627 (2019)","DOI":"10.1109\/ASRU46091.2019.9003882"},{"key":"44_CR17","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":"44_CR18","doi-asserted-by":"crossref","unstructured":"Thienpondt, J., Desplanques, B., Demuynck, K.: Cross-lingual speaker verification with domain-balanced hard prototype mining and language-dependent score normalization. arXiv preprint https:\/\/arxiv.org\/abs\/2007.07689 (2020)","DOI":"10.21437\/Interspeech.2020-2662"},{"key":"44_CR19","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. IEEE (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"44_CR20","doi-asserted-by":"crossref","unstructured":"Gao, S.: Res2Net: a new multi-scale backbone architecture. IEEE Trans. Pattern Anal. Mach. Intell. (2019)","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"44_CR21","doi-asserted-by":"crossref","unstructured":"Gao, Z., et al.: Improving aggregation and loss function for better embedding learning in end-to-end speaker verification system. In: Proceedings Interspeech 2019, pp. 361\u2013365 (2019)","DOI":"10.21437\/Interspeech.2019-1489"},{"key":"44_CR22","doi-asserted-by":"crossref","unstructured":"Thienpondt, J., Desplanques, B., Demuynck, K.: ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification. arXiv preprint https:\/\/arxiv.org\/abs\/2005.07143 (2020)","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"44_CR23","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4690\u20134699. IEEE (2019)","DOI":"10.1109\/CVPR.2019.00482"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-60276-5_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T12:51:01Z","timestamp":1723726261000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-60276-5_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030602758","9783030602765"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-60276-5_44","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"29 September 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"St. Petersburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 October 2020","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":"specom2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/specom.nw.ru\/2020\/","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":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"160","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":"65","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":"41% - 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":"5","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)"}},{"value":"Due to the Corona pandemic SPECOM 2020 was held as a virtual event","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}