{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T10:26:20Z","timestamp":1760955980545},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,8,24]],"date-time":"2019-08-24T00:00:00Z","timestamp":1566604800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,8,24]],"date-time":"2019-08-24T00:00:00Z","timestamp":1566604800000},"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":["Int J Speech Technol"],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.1007\/s10772-019-09625-6","type":"journal-article","created":{"date-parts":[[2019,8,24]],"date-time":"2019-08-24T18:02:37Z","timestamp":1566669757000},"page":"827-840","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["A new architecture based VAD for speaker diarization\/detection systems"],"prefix":"10.1007","volume":"22","author":[{"given":"Ouassila","family":"Kenai","sequence":"first","affiliation":[]},{"given":"Siham","family":"Ouamour","sequence":"additional","affiliation":[]},{"given":"Mhania","family":"Guerti","sequence":"additional","affiliation":[]},{"given":"Nassim","family":"Asbai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,8,24]]},"reference":[{"issue":"2","key":"9625_CR1","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1109\/TASL.2011.2125954","volume":"20","author":"X Anguera","year":"2012","unstructured":"Anguera, X., Bozonnet, S., Evans, N., Fredouille, C., Friedland, G., & Vinyals, O. (2012). Speaker diarization: A review of recent research. IEEE Transactions on Audio, Speech and Language Processing, 20(2), 356\u2013370.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"9625_CR2","unstructured":"Anguera, X., Wooters, C., & Hernando, J. (2006). Frame purification for cluster comparison in speaker diarization. In Second workshop on multimodal user authentication (MMUA)."},{"issue":"2","key":"9625_CR3","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1007\/s10772-017-9419-z","volume":"20","author":"N Asbai","year":"2017","unstructured":"Asbai, N., & Amrouche, A. (2017). A novel scores fusion approach applied on speaker verification under noisy environments. International Journal of Speech Technology, 20(2), 417\u2013429.","journal-title":"International Journal of Speech Technology"},{"key":"9625_CR4","unstructured":"Brookes M. (2011): VOICEBOX: A speech processing toolbox for MATLAB. http:\/\/www.ee.ic.ac.uk\/hp\/staff\/dmb\/voicebox\/voicebox.html . Accessed 1 Aug 2019."},{"key":"9625_CR5","unstructured":"Chaisorn, L., Koh, C., Zhao, Y., Xu, H., Chua, T. S., & Qi, T. (2003). Two-level multi-modal framework for news story segmentation of large video corpus. In Proceedings of TRECVID 2003 workshop. http:\/\/www-nlpir.nist.gov\/projects\/tvpubs\/tvpapers03\/nus.final.paper.pdf . Accessed 1 Aug 2019."},{"key":"9625_CR6","doi-asserted-by":"crossref","unstructured":"de Campos Niero, M., de Lima Veiga Filho, A., & Adami, A. G. (2014). A comparison of distance measures for clustering in speaker diarization. In International telecommunications symposium (ITS) (pp. 1\u20135). IEEE.","DOI":"10.1109\/ITS.2014.6947954"},{"key":"9625_CR7","unstructured":"Delacourt, P. (2000). La segmentation et le regroupement par locuteurs pour l\u2019indexation de documents audio. In These de doctorat, ENST-Eurecom (p.186)."},{"issue":"1\u20132","key":"9625_CR8","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/S0167-6393(00)00027-3","volume":"32","author":"P Delacourt","year":"2000","unstructured":"Delacourt, P., & Wellekens, C. J. (2000). DISTBIC: A speaker-based segmentation for audio data indexing. Speech Communication, 32(1\u20132), 111\u2013126. \u00a0","journal-title":"Speech Communication"},{"key":"9625_CR9","doi-asserted-by":"crossref","unstructured":"Desplanques, B., Demuynck, K., & Martens, J. P. (2015). Factor analysis for speaker segmentation and improved speaker diarization. In 16th annual conference of the international speech communication association (INTERSPEECH 2015) (pp. 3081\u20133085). International Speech Communication Association (ISCA).","DOI":"10.21437\/Interspeech.2015-106"},{"key":"9625_CR10","unstructured":"Dumpala, S. H., & Alluri, K. R. (2017). An algorithm for detection of breath sounds in spontaneous speech with application to speaker recognition. In International conference on speech and computer (pp. 98\u2013108). Cham: Springer."},{"key":"9625_CR11","unstructured":"Dupuy, G. (2015). Les collections volumineuses de documents audiovisuels: segmentation et regroupement en locuteurs (p. 249). Doctoral dissertation, Universit\u00e9 du Maine."},{"key":"9625_CR12","unstructured":"Kadri, H., Davy, M., Rabaoui, A., Lachiri, Z., & Ellouze, N. (2008). Robust audio speaker segmentation using one class SVMs. In 2008 16th European signal processing conference (pp. 1\u20135). IEEE."},{"key":"9625_CR13","doi-asserted-by":"crossref","unstructured":"Kenai, O., Asbai, N., Ouamour, S., Guerti, M., & Djeghiour, S. (2018). Speaker diarization and detection system using a priori speaker information. In 2018 2nd international conference on natural language and speech processing (ICNLSP) (pp. 1\u20136). IEEE.","DOI":"10.1109\/ICNLSP.2018.8374379"},{"key":"9625_CR14","unstructured":"Khoury, E., Meigner, S., & S\u00e9nac, C. (2008). Segmentation et regroupement en locuteurs pour la parole conversationnelle. In XXVIIe Journ\u00e9es d\u2019\u00e9tude sur la parole (JEP 2008) (p. 4)."},{"key":"9625_CR15","doi-asserted-by":"crossref","unstructured":"Kinnunen, T., & Rajan, P. (2013). A practical, self-adaptive voice activity detector for speaker verification with noisy telephone and microphone data. In 2013 IEEE international conference on acoustics, speech and signal processing (pp. 7229\u20137233). IEEE.","DOI":"10.1109\/ICASSP.2013.6639066"},{"key":"9625_CR16","unstructured":"Kozlov, A., Kudashev, O., Matveev, Y., Pekhovsky, T., Simonchik, K., & Shulipa, A. (2013). SVID speaker recognition system for NIST SRE 2012. In International conference on speech and computer (pp. 278\u2013285). Cham: Springer."},{"key":"9625_CR17","unstructured":"Lamy, R., Moraru, D., Bigi, B., & Besacier, L. (2004). Premiers pas du CLIPS sur les donn\u00e9es d\u2019\u00e9valuation ESTER. In Proc. of Journ\u00e9es d\u2019Etude de la Parole, F\u00e8s, Maroc."},{"key":"9625_CR18","unstructured":"Lauer, F., & Bloch, G. (2006). M\u00e9thodes SVM pour l\u2019identification. In Journ\u00e9es Identification et Mod\u00e9lisation Exp\u00e9rimentale JIME\u20192006, Poitiers, France. CDROM."},{"key":"9625_CR19","unstructured":"Meignier, S., & Merlin, T. (2010). LIUM_SpkDiarization: An open source toolkit for diarization. In CMU SPUD, workshop, 2010, Dallas."},{"issue":"3","key":"9625_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4018\/jmdem.2012070101","volume":"3","author":"R Mertens","year":"2012","unstructured":"Mertens, R., Huang, P. S., Gottlieb, L., Friedland, G., Divakaran, A., & Hasegawa-Johnson, M. (2012). On the applicability of speaker diarization to audio indexing of non-speech and mixed non-speech\/speech video soundtracks. International Journal of Multimedia Data Engineering and Management (IJMDEM), 3(3), 1\u201319.","journal-title":"International Journal of Multimedia Data Engineering and Management (IJMDEM)"},{"key":"9625_CR21","first-page":"9","volume-title":"Speaker diarization in the ELISA consortium over the last 4\u00a0years","author":"D Moraru","year":"2004","unstructured":"Moraru, D., Besacier, L., Meignier, S., Fredouille, C., & Bonastre, J. F. (2004a). Speaker diarization in the ELISA consortium over the last 4\u00a0years (p. 9). New York: Palisades."},{"key":"9625_CR22","unstructured":"Moraru, D., Meignier, S., Fredouille, C., Besacier, L., & Bonastre, J. F. (2004b). ELISA Nist RT03 broadcast news speaker diarization experiments. In ODYSSEY04\u2014The speaker and language recognition workshop, Toledo, Spain (p. 6)."},{"key":"9625_CR23","unstructured":"Nguyen, T., Sun, H., Zhao, S., Khine, S. Z. K., Tran, H. D., Ma, T. L. N., et al. (2009). The IIR-NTU speaker diarization systems for RT 2009. In RT\u201909, NIST rich transcription workshop, May 28\u201329, 2009, Melbourne, FL (Vol. 14, pp. 17\u201340)."},{"key":"9625_CR24","first-page":"2011","volume-title":"NIST speaker recognition evaluation training data LDC2011S01. Web Download","author":"NIST Multimodal Information Group","year":"2005","unstructured":"NIST Multimodal Information Group. (2005). NIST speaker recognition evaluation training data LDC2011S01. Web Download (p. 2011). Philadelphia: Linguistic Data Consortium."},{"issue":"1","key":"9625_CR25","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1109\/TMM.2004.840604","volume":"7","author":"C Panagiotakis","year":"2005","unstructured":"Panagiotakis, C., & Tziritas, G. (2005). A speech\/music discriminator based on RMS and zero-crossings. IEEE Transactions on Multimedia, 7(1), 155\u2013166.","journal-title":"IEEE Transactions on Multimedia"},{"key":"9625_CR26","unstructured":"Parlangeau-Vall\u00e8s, N., Farinas, J., Fohr, D., Illina, I., Magrin-Chagnolleau, I., Mella, O., et al. (2003). Audio indexing on the web: A preliminary study of some audio descriptors. In 7th world multiconference on systematics, cybernetics and informatics-SCI\u20192003 (p. 4)."},{"key":"9625_CR27","unstructured":"Prazak, J., & Silovsky, J. (2011). Comparison of segmentation and clustering methods for speaker diarization of broadcast stream audio. In Analysis of verbal and nonverbal communication and enactment. The processing issues (pp. 214\u2013222). Berlin: Springer."},{"issue":"1\u20133","key":"9625_CR28","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1006\/dspr.1999.0361","volume":"10","author":"DA Reynolds","year":"2000","unstructured":"Reynolds, D. A., Quatieri, T. F., & Dunn, R. B. (2000). Speaker verification using adapted Gaussian mixture models. Digital Signal Processing, 10(1\u20133), 19\u201341.","journal-title":"Digital Signal Processing"},{"issue":"7","key":"9625_CR29","first-page":"1109","volume":"119","author":"AA Shabana","year":"2018","unstructured":"Shabana, A. A., Lavanya, T., & Vijayalakshmi, P. (2018). Speaker diarization for conversational speech using Bayesian information criterion. International Journal of Pure and Applied Mathematics, 119(7), 1109\u20131114.","journal-title":"International Journal of Pure and Applied Mathematics"},{"key":"9625_CR30","unstructured":"Shulipa, A., Sholohov, A., & Matveev, Y. (2017). Clustering target speaker on a set of telephone dialogs. In International conference on speech and computer (pp. 244\u2013252). Cham: Springer."},{"key":"9625_CR31","unstructured":"Tranter, S., & Reynolds, D. (2004). Speaker diarisation for broadcast news. In Odyssey04\u2014The speaker and language recognition workshop."},{"key":"9625_CR32","unstructured":"Veiga, A., Lopes, C., & Perdig\u00e3o, F. (2010). Speaker diarization using gaussian mixture turns and segment matching. In Proc. FALA."},{"issue":"3","key":"9625_CR33","doi-asserted-by":"publisher","first-page":"183","DOI":"10.2498\/cit.1001067","volume":"16","author":"B Vesnicer","year":"2008","unstructured":"Vesnicer, B., Mihelic, F., & Zibert, J. (2008). Development of a speaker diarization system for speaker tracking in audio broadcast news: a case study. Journal of Computing and Information Technology, 16(3), 183\u2013195.","journal-title":"Journal of Computing and Information Technology"},{"key":"9625_CR34","unstructured":"Wang, G., Wu, X., Zheng, T. F., Wang, L., & Zhang, C. (2011). Using class purity as criterion for speaker clustering in multi-speaker detection tasks. In APSIPA ASC 2011 Xi\u2019an."},{"key":"9625_CR35","unstructured":"Zhu, X., Barras, C., Lamel, L., & Gauvain, J. L. (2007). Multi-stage speaker diarization for conference and lecture meetings. In Multimodal technologies for perception of humans (pp. 533\u2013542). Berlin: Springer."},{"issue":"1","key":"9625_CR36","first-page":"51","volume":"32","author":"J \u017dibert","year":"2008","unstructured":"\u017dibert, J., Vesnicer, B., & Mihelic, F. (2008). A system for speaker detection and tracking in audio broadcast news. Informatica, 32(1), 51\u201361.","journal-title":"Informatica"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-019-09625-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-019-09625-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-019-09625-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,26]],"date-time":"2022-09-26T09:48:17Z","timestamp":1664185697000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-019-09625-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,24]]},"references-count":36,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,9]]}},"alternative-id":["9625"],"URL":"https:\/\/doi.org\/10.1007\/s10772-019-09625-6","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8,24]]},"assertion":[{"value":"2 March 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 August 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 August 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}