{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:58:43Z","timestamp":1740099523037,"version":"3.37.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030260606"},{"type":"electronic","value":"9783030260613"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","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":[[2019]]},"DOI":"10.1007\/978-3-030-26061-3_56","type":"book-chapter","created":{"date-parts":[[2019,8,8]],"date-time":"2019-08-08T23:03:54Z","timestamp":1565305434000},"page":"549-558","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Diarization of the Language Consulting Center Telephone Calls"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4153-6560","authenticated-orcid":false,"given":"Zbyn\u011bk","family":"Zaj\u00edc","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4761-1645","authenticated-orcid":false,"given":"Josef V.","family":"Psutka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0021-5365","authenticated-orcid":false,"given":"Lucie","family":"Zaj\u00edcov\u00e1","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6581-6348","authenticated-orcid":false,"given":"Lud\u011bk","family":"M\u00fcller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4238-8077","authenticated-orcid":false,"given":"Petr","family":"Salajka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,7,24]]},"reference":[{"key":"56_CR1","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1007\/978-3-319-10816-2_56","volume-title":"Text, Speech and Dialogue","author":"P Campr","year":"2014","unstructured":"Campr, P., Kune\u0161ov\u00e1, M., Van\u011bk, J., \u010cech, J., Psutka, J.: Audio-video speaker diarization for unsupervised speaker and face model creation. In: Sojka, P., Hor\u00e1k, A., Kope\u010dek, I., Pala, K. (eds.) TSD 2014. LNCS (LNAI), vol. 8655, pp. 465\u2013472. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10816-2_56"},{"key":"56_CR2","unstructured":"Canavan, A., Graff, D., Zipperlen, G.: CALLHOME American English speech, LDC97S42. In: LDC Catalog. Linguistic Data Consortium, Philadelphia (1997)"},{"key":"56_CR3","doi-asserted-by":"crossref","unstructured":"Diez, M., et al.: BUT system for DIHARD speech diarization challenge 2018. In: Intespeech, Hyderabad, pp. 2798\u20132802 (2018)","DOI":"10.21437\/Interspeech.2018-1749"},{"key":"56_CR4","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1007\/11965152_28","volume":"4299","author":"JG Fiscus","year":"2006","unstructured":"Fiscus, J.G., Radde, N., Garofolo, J.S., Le, A., Ajot, J., Laprun, C.: The rich transcription 2006 spring meeting recognition evaluation. Mach. Learn. Multimodal Interact. 4299, 309\u2013322 (2006)","journal-title":"Mach. Learn. Multimodal Interact."},{"key":"56_CR5","doi-asserted-by":"crossref","unstructured":"Geiger, J.T., Wallhoff, F., Rigoll, G.: $$\\{{\\rm GMM}\\}$$ - $$\\{{\\rm UBM}\\}$$ based open-setonline speaker diarization. In: Interspeech, Makuhari, pp. 2330\u20132333 (2010)","DOI":"10.21437\/Interspeech.2010-638"},{"key":"56_CR6","doi-asserted-by":"crossref","unstructured":"Hr\u00faz, M., Zaj\u00edc, Z.: Convolutional neural network for speaker change detection in telephone speaker diarization system. In: ICASSP, pp. 4945\u20134949. IEEE, New Orleans (2017)","DOI":"10.1109\/ICASSP.2017.7953097"},{"key":"56_CR7","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/11744085_41","volume":"3954","author":"S Ioffe","year":"2006","unstructured":"Ioffe, S.: Probabilistic linear discriminant analysis. Lect. Notes Comput. Sci. 3954, 531\u2013542 (2006)","journal-title":"Lect. Notes Comput. Sci."},{"issue":"6","key":"56_CR8","doi-asserted-by":"publisher","first-page":"1059","DOI":"10.1109\/JSTSP.2010.2081790","volume":"4","author":"P Kenny","year":"2010","unstructured":"Kenny, P., Reynolds, D., Castaldo, F.: Diarization of telephone conversations using factor analysis. IEEE J. Sel. Top. Sign. Proces. 4(6), 1059\u20131070 (2010)","journal-title":"IEEE J. Sel. Top. Sign. Proces."},{"key":"56_CR9","doi-asserted-by":"crossref","unstructured":"Rouvier, M., Dupuy, G., Gay, P., Khoury, E., Merlin, T., Meignier, S.: An open-source state-of-the-art toolbox for broadcast news diarization. In: Interspeech, Lyon, pp. 1477\u20131481 (2013)","DOI":"10.21437\/Interspeech.2013-383"},{"key":"56_CR10","unstructured":"Ryant, N., et al.: DIHARD Corpus. Technical report, LDC (2018)"},{"key":"56_CR11","unstructured":"Ryant, N., Church, K., Cieri, C., Cristia, A., Du, J., Ganapathy, S., Liberman, M.: DIHARD Corpus. Technical report, LDC (2019)"},{"key":"56_CR12","doi-asserted-by":"crossref","unstructured":"Ryant, N., et al.: The second DIHARD diarization challenge: dataset, task, and baselines. In: INTERSPEECH, Gratz (2019)","DOI":"10.21437\/Interspeech.2019-1268"},{"key":"56_CR13","doi-asserted-by":"crossref","unstructured":"Sell, G., Garcia-Romero, D.: Speaker diarization with PLDA I-vector scoring and unsupervised calibration. In: IEEE Spoken Language Technology Workshop, South Lake Tahoe, pp. 413\u2013417 (2014)","DOI":"10.1109\/SLT.2014.7078610"},{"key":"56_CR14","doi-asserted-by":"crossref","unstructured":"Sell, G., et al.: Diarization is hard: some experiences and lessons learned for the JHU team in the inaugural DIHARD challenge. In: Interspeech, Hyderabad, pp. 2808\u20132812 (2018)","DOI":"10.21437\/Interspeech.2018-1893"},{"key":"56_CR15","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1109\/TASLP.2013.2285474","volume":"22","author":"M Senoussaoui","year":"2014","unstructured":"Senoussaoui, M., Kenny, P., Stafylakis, T., Dumouchel, P.: A study of the cosine distance-based mean shift for telephone speech diarization. Audio Speech Lang. Proces. 22, 217\u2013227 (2014)","journal-title":"Audio Speech Lang. Proces."},{"key":"56_CR16","doi-asserted-by":"crossref","unstructured":"Shum, S., Dehak, N., Chuangsuwanich, E., Reynolds, D., Glass, J.: Exploiting intra-conversation variability for speaker diarization. In: Interspeech, pp. 945\u2013948. Florence (2011)","DOI":"10.21437\/Interspeech.2011-383"},{"issue":"10","key":"56_CR17","doi-asserted-by":"publisher","first-page":"2015","DOI":"10.1109\/TASL.2013.2264673","volume":"21","author":"SH Shum","year":"2013","unstructured":"Shum, S.H., Dehak, N., Dehak, R., Glass, J.R.: Unsupervised methods for speaker diarization: an integrated and iterative approach. Audio Speech Lang. Proces. 21(10), 2015\u20132028 (2013)","journal-title":"Audio Speech Lang. Proces."},{"key":"56_CR18","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Sell, G., Povey, D., Khudanpur, S.: X-Vectors: robust DNN embeddings for speaker recognition. In: ICASSP, pp. 5329\u20135333 (2018)","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"56_CR19","doi-asserted-by":"crossref","unstructured":"Sun, L., et al.: Speaker diarization with enhancing speech for the first DIHARD challenge. In: Interspeech, pp. 2793\u20132797 (2018)","DOI":"10.21437\/Interspeech.2018-1742"},{"key":"56_CR20","doi-asserted-by":"crossref","unstructured":"Wang, Q., Downey, C., Wan, L., Mansfield, P.A., Moreno, I.L.: Speaker diarization with LSTM. In: ICASSP, Calgary, pp. 5239\u20135243 (2017)","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"56_CR21","doi-asserted-by":"crossref","unstructured":"Wang, R., Gu, M., Li, L., Xu, M., Zheng, T.F.: Speaker segmentation using deep speaker vectors for fast speaker change scenarios. In: ICASSP, pp. 5420\u20135424. IEEE, New Orleans (2017)","DOI":"10.1109\/ICASSP.2017.7953192"},{"key":"56_CR22","doi-asserted-by":"crossref","unstructured":"Zaj\u00edc, Z., Hr\u00faz, M., M\u00fcller, L.: Speaker diarization using convolutional neural network for statistics accumulation refinement. In: Interpeech, Stockholm, pp. 3562\u20133566 (2017)","DOI":"10.21437\/Interspeech.2017-51"},{"key":"56_CR23","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1007\/978-3-319-43958-7_49","volume-title":"Speech and Computer","author":"Z Zaj\u00edc","year":"2016","unstructured":"Zaj\u00edc, Z., Kune\u0161ov\u00e1, M., Radov\u00e1, V.: Investigation of segmentation in i-vector based speaker diarization of telephone speech. In: Ronzhin, A., Potapova, R., N\u00e9meth, G. (eds.) SPECOM 2016. LNCS (LNAI), vol. 9811, pp. 411\u2013418. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-43958-7_49"},{"key":"56_CR24","doi-asserted-by":"crossref","unstructured":"Zaj\u00edc, Z., Kune\u0161ov\u00e1, M., Zelinka, J., Hr\u00faz, M.: ZCU-NTIS speaker diarization system for the DIHARD 2018 challenge. In: Interspeech, Hyderabad, pp. 2788\u20132792 (2018)","DOI":"10.21437\/Interspeech.2018-1252"},{"key":"56_CR25","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"778","DOI":"10.1007\/978-3-319-99579-3_79","volume-title":"Speech and Computer","author":"Z Zaj\u00edc","year":"2018","unstructured":"Zaj\u00edc, Z., et al.: First insight into the processing of the language consulting center data. In: Karpov, A., Jokisch, O., Potapova, R. (eds.) SPECOM 2018. LNCS (LNAI), vol. 11096, pp. 778\u2013787. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-99579-3_79"},{"key":"56_CR26","unstructured":"Zaj\u00edc, Z., Kune\u0161ov\u00e1, M., Hr\u00faz, M., Van\u011bk, J.: UWB-NTIS speaker diarization system for the DIHARD II 2019 challenge. In: Submitted to Interspeech 2019. Gratz (2019). https:\/\/arxiv.org\/abs\/1905.11276"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-26061-3_56","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,25]],"date-time":"2022-09-25T10:29:35Z","timestamp":1664101775000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-26061-3_56"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030260606","9783030260613"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-26061-3_56","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"24 July 2019","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":"Istanbul","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turkey","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 August 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 August 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/specom.nw.ru\/2019\/","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":"86","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":"57","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":"66% - 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)"}}]}}