{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T18:49:10Z","timestamp":1743101350392,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031209796"},{"type":"electronic","value":"9783031209802"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20980-2_3","type":"book-chapter","created":{"date-parts":[[2022,11,12]],"date-time":"2022-11-12T19:03:09Z","timestamp":1668279789000},"page":"24-32","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep Speaker Embeddings Based Online Diarization"],"prefix":"10.1007","author":[{"given":"Anastasia","family":"Avdeeva","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergey","family":"Novoselov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,10]]},"reference":[{"key":"3_CR1","unstructured":"Ardila, R., et al.: Common voice: a massively-multilingual speech corpus. In: LREC (2020)"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Bredin, H., et al.: Pyannote.audio: neural building blocks for speaker diarization. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7124\u20137128 (2020)","DOI":"10.1109\/ICASSP40776.2020.9052974"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Carletta, J., et al.: The ami meeting corpus: a pre-announcement. In: MLMI (2005)","DOI":"10.1007\/11677482_3"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Dawalatabad, N., Ravanelli, M., Grondin, F., Thienpondt, J., Desplanques, B., Na, H.: Ecapa-tdnn embeddings for speaker diarization. In: Interspeech (2021)","DOI":"10.21437\/Interspeech.2021-941"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"D\u00edez, M., Burget, L., Landini, F., Wang, S., \u010cernock\u00fd, J.H.: Optimizing bayesian hmm based x-vector clustering for the second dihard speech diarization challenge. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6519\u20136523 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053982"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., Sun, J.: Repvgg: making vgg-style convnets great again. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13728\u201313737 (2021)","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Fini, E., Brutti, A.: Supervised online diarization with sample mean loss for multi-domain data. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7134\u20137138 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053477"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Fujita, Y., Kanda, N., Horiguchi, S., Nagamatsu, K., Watanabe, S.: End-to-end neural speaker diarization with permutation-free objectives. In: INTERSPEECH (2019)","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Horiguchi, S., Fujita, Y., Watanabe, S., Xue, Y., Nagamatsu, K.: End-to-end speaker diarization for an unknown number of speakers with encoder-decoder based attractors. ArXiv abs\/2005.09921 (2020)","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"3_CR10","unstructured":"Horiguchi, S., Watanabe, S., Garc\u00eda, P., Takashima, Y., Kawaguchi, Y.: Online neural diarization of unlimited numbers of speakers. ArXiv abs\/2206.02432 (2022)"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Isik, Y.Z., Roux, J.L., Chen, Z., Watanabe, S., Hershey, J.R.: Single-channel multi-speaker separation using deep clustering. In: INTERSPEECH (2016)","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"3_CR12","doi-asserted-by":"publisher","unstructured":"Kanda, N., et al.: Guided source separation meets a strong ASR backend: hitachi\/paderborn university joint investigation for dinner party ASR. In: Proceedings of Interspeech 2019, pp. 1248\u20131252 (2019). https:\/\/doi.org\/10.21437\/Interspeech.2019-1167","DOI":"10.21437\/Interspeech.2019-1167"},{"key":"3_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101254","volume":"71","author":"F Landini","year":"2022","unstructured":"Landini, F., Profant, J., Diez, M., Burget, L.: Bayesian hmm clustering of x-vector sequences (vbx) in speaker diarization: theory, implementation and analysis on standard tasks. Comput. Speech Lang. 71, 101254 (2022)","journal-title":"Comput. Speech Lang."},{"key":"3_CR14","unstructured":"Landini, F., Profant, J., D\u00edez, M., Burget, L.: Bayesian hmm clustering of x-vector sequences (vbx) in speaker diarization: theory, implementation and analysis on standard tasks. ArXiv abs\/2012.14952 (2020)"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Lavrentyeva, G., et al.: Blind speech signal quality estimation for speaker verification systems. In: INTERSPEECH (2020)","DOI":"10.21437\/Interspeech.2020-1826"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Martin, A.F., Greenberg, C.S.: Nist 2008 speaker recognition evaluation: performance across telephone and room microphone channels. In: INTERSPEECH (2009)","DOI":"10.21437\/Interspeech.2009-679"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Medennikov, I., et al.: Target-speaker voice activity detection: a novel approach for multi-speaker diarization in a dinner party scenario. ArXiv abs\/2005.07272 (2020)","DOI":"10.21437\/Interspeech.2020-1602"},{"key":"3_CR18","unstructured":"Morrone, G., Cornell, S., Raj, D., Zovato, E., Brutti, A., Squartini, S.: Leveraging speech separation for conversational telephone speaker diarization (2022)"},{"key":"3_CR19","unstructured":"Novoselov, S., Lavrentyeva, G., Avdeeva, A., Volokhov, V., Gusev, A.: Robust speaker recognition with transformers using wav2vec 2.0. ArXiv abs\/2203.15095 (2022)"},{"key":"3_CR20","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1109\/LSP.2019.2961071","volume":"27","author":"TJ Park","year":"2020","unstructured":"Park, T.J., Han, K.J., Kumar, M., Narayanan, S.S.: Auto-tuning spectral clustering for speaker diarization using normalized maximum eigengap. IEEE Signal Process. Lett. 27, 381\u2013385 (2020)","journal-title":"IEEE Signal Process. Lett."},{"key":"3_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101317","volume":"72","author":"TJ Park","year":"2022","unstructured":"Park, T.J., Kanda, N., Dimitriadis, D., Han, K.J., Watanabe, S., Narayanan, S.S.: A review of speaker diarization: recent advances with deep learning. Comput. Speech Lang. 72, 101317 (2022)","journal-title":"Comput. Speech Lang."},{"key":"3_CR22","unstructured":"Qin, X., et al.: The ffsvc 2020 evaluation plan. ArXiv abs\/2002.00387 (2020)"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Ryant, N., et al.: The second dihard diarization challenge: dataset, task, and baselines. In: INTERSPEECH (2019)","DOI":"10.21437\/Interspeech.2019-1268"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Wang, W., Lin, Q., Li, M.: Online target speaker voice activity detection for speaker diarization. ArXiv abs\/2207.05920 (2022)","DOI":"10.21437\/Interspeech.2022-677"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Xue, Y., et al.: Online end-to-end neural diarization handling overlapping speech and flexible numbers of speakers. ArXiv abs\/2101.08473 (2021)","DOI":"10.21437\/Interspeech.2021-708"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Yu, D., Kolb\u00e6k, M., Tan, Z., Jensen, J.H.: Permutation invariant training of deep models for speaker-independent multi-talker speech separation. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 241\u2013245 (2017)","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, A., Wang, Q., Zhu, Z., Paisley, J.W., Wang, C.: Fully supervised speaker diarization. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6301\u20136305 (2019)","DOI":"10.1109\/ICASSP.2019.8683892"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Online speaker diarization with graph-based label generation. In: Odyssey (2022)","DOI":"10.21437\/Odyssey.2022-23"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20980-2_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,12]],"date-time":"2022-11-12T19:03:52Z","timestamp":1668279832000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20980-2_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031209796","9783031209802"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20980-2_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"10 November 2022","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":"Gurugram","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.specom.co.in","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":"99","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":"60","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":"61% - 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":"4","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)"}}]}}