{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:01:44Z","timestamp":1760709704171,"version":"3.41.0"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030007935"},{"type":"electronic","value":"9783030007942"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-00794-2_37","type":"book-chapter","created":{"date-parts":[[2018,9,7]],"date-time":"2018-09-07T19:50:24Z","timestamp":1536349824000},"page":"342-350","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Recurrent Neural Network Based Speaker Change Detection from Text Transcription Applied in Telephone Speaker Diarization System"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4153-6560","authenticated-orcid":false,"given":"Zbyn\u011bk","family":"Zaj\u00edc","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8899-8260","authenticated-orcid":false,"given":"Daniel","family":"Soutner","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7851-9879","authenticated-orcid":false,"given":"Marek","family":"Hr\u00faz","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6581-6348","authenticated-orcid":false,"given":"Lud\u011bk","family":"M\u00fcller","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3258-8430","authenticated-orcid":false,"given":"Vlasta","family":"Radov\u00e1","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,9,8]]},"reference":[{"key":"37_CR1","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":"37_CR2","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":"37_CR3","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, New Orleans, pp. 4945\u20134949 (2017)","DOI":"10.1109\/ICASSP.2017.7953097"},{"key":"37_CR4","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"},{"issue":"4","key":"37_CR5","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2011","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 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"37_CR6","doi-asserted-by":"crossref","unstructured":"Shum, S., Dehak, N., Chuangsuwanich, E., Reynolds, D., Glass, J.: Exploiting intra-conversation variability for speaker diarization. In: Interspeech, Florence, pp. 945\u2013948 (2011)","DOI":"10.21437\/Interspeech.2011-383"},{"key":"37_CR7","doi-asserted-by":"crossref","unstructured":"Valente, F., Vijayasenan, D., Motlicek, P.: Speaker diarization of meetings based on speaker role n-gram models. In: ICASSP, pp. 4416\u20134419. IEEE, Prague (2011)","DOI":"10.1109\/ICASSP.2011.5947333"},{"key":"37_CR8","doi-asserted-by":"crossref","unstructured":"Tranter, S.E., Yu, K., Evermann, G., Woodland, P.C.: Generating and evaluating segmentations for automatic speech recognition of conversational telephone speech. In: ICASSP, pp. 753\u2013756. IEEE, Montreal (2004)","DOI":"10.1109\/ICASSP.2004.1326095"},{"key":"37_CR9","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1007\/978-3-319-64206-2_48","volume-title":"Text, Speech, and Dialogue","author":"M Kune\u0161ov\u00e1","year":"2017","unstructured":"Kune\u0161ov\u00e1, M., Zaj\u00edc, Z., Radov\u00e1, V.: Experiments with segmentation in an online speaker diarization system. In: Ek\u0161tein, K., Matou\u0161ek, V. (eds.) TSD 2017. LNCS (LNAI), vol. 10415, pp. 429\u2013437. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-64206-2_48"},{"key":"37_CR10","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1007\/978-3-319-43958-7_22","volume-title":"Speech and Computer","author":"M Hr\u00faz","year":"2016","unstructured":"Hr\u00faz, M., Kune\u0161ov\u00e1, M.: Convolutional neural network in the task of speaker change detection. In: Ronzhin, A., Potapova, R., N\u00e9meth, G. (eds.) SPECOM 2016. LNCS (LNAI), vol. 9811, pp. 191\u2013198. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-43958-7_22"},{"key":"37_CR11","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/978-3-642-40585-3_14","volume-title":"Text, Speech, and Dialogue","author":"D Soutner","year":"2013","unstructured":"Soutner, D., M\u00fcller, L.: Application of LSTM neural networks in language modelling. In: Habernal, I., Matou\u0161ek, V. (eds.) TSD 2013. LNCS (LNAI), vol. 8082, pp. 105\u2013112. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-40585-3_14"},{"issue":"8","key":"37_CR12","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Urgen Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"37_CR13","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1007\/978-3-642-32790-2_58","volume-title":"Text, Speech and Dialogue","author":"Z Zaj\u00edc","year":"2012","unstructured":"Zaj\u00edc, Z., Machlica, L., M\u00fcller, L.: Robust adaptation techniques dealing with small amount of data. In: Sojka, P., Hor\u00e1k, A., Kope\u010dek, I., Pala, K. (eds.) TSD 2012. LNCS (LNAI), vol. 7499, pp. 480\u2013487. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-32790-2_58"},{"key":"37_CR14","unstructured":"Kenny, P., Dumouchel, P.: Experiments in speaker verification using factor analysis likelihood ratios. In: Odyssey, Toledo, pp. 219\u2013226 (2004)"},{"key":"37_CR15","unstructured":"Canavan, A., Graff, D., Zipperlen, G.: CALLHOME American English speech, LDC97S42. In: LDC Catalog. Linguistic Data Consortium, Philadelphia (1997)"},{"key":"37_CR16","unstructured":"Godfrey, J.J., Holliman, E.: Switchboard-1 release 2. In: LDC Catalog. Linguistics Data Consortium, Philadelphia (1997)"},{"key":"37_CR17","unstructured":"Daniel, P., et al.: Modelos animales de dolor neurop\u00e1tico. In: Workshop on Automatic Speech Recognition and Understanding, IEEE Catalog No.: CFP11SRW-USB (2011)"},{"key":"37_CR18","doi-asserted-by":"crossref","unstructured":"Harris, M., Aubert, X., Haeb-Umbach, R., Beyerlein, P.: A study of broadcast news audio stream segmentation and segment clustering. In: EUROSPEECH, Budapest, pp. 1027\u20131030 (1999)","DOI":"10.21437\/Eurospeech.1999-166"},{"key":"37_CR19","doi-asserted-by":"crossref","unstructured":"Bredin, H.: TristouNet: triplet loss for speaker turn embedding. In: ICASSP, New Orleans, pp. 5430\u20135434 (2017)","DOI":"10.1109\/ICASSP.2017.7953194"},{"key":"37_CR20","doi-asserted-by":"crossref","unstructured":"Bredin, H.: pyannote.metrics: a toolkit for reproducible evaluation, diagnostic, and error analysis of speaker diarization systems. In: Interspeech, Stockholm, pp. 3587\u20133591 (2017)","DOI":"10.21437\/Interspeech.2017-411"},{"key":"37_CR21","doi-asserted-by":"crossref","unstructured":"Sell, G., Garcia-Romero, D., Mccree, A.: Speaker diarization with I-vectors from DNN senone posteriors. In: Interspeech, Dresden, pp. 3096\u20133099 (2015)","DOI":"10.21437\/Interspeech.2015-109"},{"key":"37_CR22","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":"37_CR23","doi-asserted-by":"crossref","unstructured":"India, M., Fonollosa, J., Hernando, J.: LSTM neural network-based speaker segmentation using acoustic and language modelling. In: Interspeech, Stockholm, pp. 2834\u20132838 (2017)","DOI":"10.21437\/Interspeech.2017-407"}],"container-title":["Lecture Notes in Computer Science","Text, Speech, and Dialogue"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-00794-2_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T00:28:47Z","timestamp":1751848127000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-00794-2_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030007935","9783030007942"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-00794-2_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"8 September 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}