{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T14:16:00Z","timestamp":1740147360993,"version":"3.37.3"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T00:00:00Z","timestamp":1580342400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T00:00:00Z","timestamp":1580342400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100002850","name":"Fondo Nacional de Desarrollo Cient\u00edfico y Tecnol\u00f3gico","doi-asserted-by":"publisher","award":["3190147","11180107","11160517"],"award-info":[{"award-number":["3190147","11180107","11160517"]}],"id":[{"id":"10.13039\/501100002850","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.1007\/s11760-020-01634-2","type":"journal-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T16:02:40Z","timestamp":1580400160000},"page":"1017-1025","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A novel method for estimating the number of speakers based on generalized eigenvalue\u2013vector decomposition and adaptive wavelet transform by using K-means clustering"],"prefix":"10.1007","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6391-6863","authenticated-orcid":false,"given":"Ali","family":"Dehghan Firoozabadi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pablo","family":"Irarrazaval","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pablo","family":"Adasme","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Zabala-Blanco","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cesar","family":"Azurdia-Meza","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,1,30]]},"reference":[{"key":"1634_CR1","unstructured":"Nakashima, H., Mukai, T.: 3D sound source localization system based on learning of binaural hearing. In: Proceedings of IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 3534\u20133539 (2005)"},{"key":"1634_CR2","doi-asserted-by":"crossref","unstructured":"Ikeda, A., Mizoguchi, H., Sasaki, Y., Enomoto, T., Kagami, S.: 2D sound source localization in azimuth and elevation from microphone array by using a directional pattern of element. In: Proceedings of IEEE Sensors, pp. 1213\u20131216 (2007)","DOI":"10.1109\/ICSENS.2007.4388627"},{"key":"1634_CR3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-04619-7","volume-title":"Microphone Arrays","author":"M Brandstein","year":"2001","unstructured":"Brandstein, M., Ward, D.: Microphone Arrays. Springer, Berlin (2001)"},{"issue":"23","key":"1634_CR4","doi-asserted-by":"publisher","first-page":"6118","DOI":"10.1109\/TSP.2013.2283462","volume":"61","author":"K Han","year":"2013","unstructured":"Han, K., Nehorai, A.: Improved source number detection and direction estimation with nested arrays and ULAs using jackknifing. IEEE Trans. Signal Process. 61(23), 6118\u20136128 (2013)","journal-title":"IEEE Trans. Signal Process."},{"key":"1634_CR5","unstructured":"Arai, T.: Estimating number of speakers by the modulation characteristics of speech. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 197\u2013200 (2003)"},{"key":"1634_CR6","doi-asserted-by":"crossref","unstructured":"Zwyssig, E., Renals, S., Lincoln, M.: Determining the number of speakers in a meeting using microphone array features. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4765\u20134768 (2012)","DOI":"10.1109\/ICASSP.2012.6288984"},{"issue":"7","key":"1634_CR7","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1109\/LSP.2006.891333","volume":"14","author":"R Swamy","year":"2007","unstructured":"Swamy, R., Murty, K., Yegnanarayana, B.: Determining number of speakers from multispeaker speech signals using excitation source information. IEEE Signal Process. Lett. 14(7), 481\u2013484 (2007)","journal-title":"IEEE Signal Process. Lett."},{"key":"1634_CR8","doi-asserted-by":"crossref","unstructured":"Vinals, I., Gimeno, P., Ortega, A., Miguel, A., Lleida, E.: Estimation of the number of speakers with variational Bayesian PLDA in the DIHARD Diarization challenge. In: Proceedings of Interspeech 2018, pp. 2803\u20132807 (2018)","DOI":"10.21437\/Interspeech.2018-1841"},{"issue":"2","key":"1634_CR9","first-page":"101","volume":"1","author":"H Sayoud","year":"2010","unstructured":"Sayoud, H., Ouamour, S.: Proposal of a new condense parameter estimating the number of speakers\u2014an experimental investigation. J. Inf. Hiding Multimed. Signal Process. 1(2), 101\u2013109 (2010)","journal-title":"J. Inf. Hiding Multimed. Signal Process."},{"key":"1634_CR10","unstructured":"Kumar, A., Balakrishna, P.V., Prakesh, C., Gangashetty, S.V.: Bessel features for estimating number of speakers from multispeaker speech signals. In: Proceedings of 18th International Conference on Systems, Signals and Image Processing (IWSSIP), pp. 1\u20134 (2011)"},{"key":"1634_CR11","doi-asserted-by":"crossref","unstructured":"St\u00f6ter, F.R.; Chakrabarty, S., Edler, B., Habets, E.A.P.: Classification versus regression in supervised learning for single channel speaker count estimation. In: Proceedings of 43rd International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 436\u2013440 (2018)","DOI":"10.1109\/ICASSP.2018.8462159"},{"key":"1634_CR12","doi-asserted-by":"crossref","unstructured":"Maka, T., Lazoryszczak, M.: Detecting the number of speakers in speech mixtures by human and machine. In: Proceedings of 22nd Signal Processing, Algorithms, Architectures, Arrangements, and Applications (SPA), pp. 239\u2013244 (2018)","DOI":"10.23919\/SPA.2018.8563405"},{"issue":"2","key":"1634_CR13","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1109\/TASLP.2018.2877892","volume":"27","author":"FR St\u00f6ter","year":"2019","unstructured":"St\u00f6ter, F.R., Chakrabarty, S., Edler, B., Habets, E.A.P.: CountNet: estimating the number of concurrent speakers using supervised learning. IEEE\/ACM Trans. Audio Speech Lang. Process. 27(2), 268\u2013282 (2019)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"1634_CR14","unstructured":"Rickard, S., Dietrich, F.: DOA estimation of many W-disjoint orthogonal sources from two mixtures using DUET. In: Proceedings of 10th IEEE Workshop on Statistical Signal and Array Processing (SSAP), pp. 311\u2013314 (2000)"},{"key":"1634_CR15","doi-asserted-by":"crossref","unstructured":"Santen, V., Sproat, J.: High-accuracy automatic segmentation. In: Proceedings of EUROSPEECH, pp. 2809\u20132812 (1999)","DOI":"10.21437\/Eurospeech.1999-620"},{"key":"1634_CR16","unstructured":"Dehghan Firoozabadi, A.: Extension and improvement of the methods for the localization of multiple simultaneous speech sources. PhD thesis, Electrical Engineering, Yazd University (2015)"},{"issue":"4","key":"1634_CR17","first-page":"248","volume":"7","author":"G Ghodrati Amiri","year":"2009","unstructured":"Ghodrati Amiri, G., Asadi, A.: Comparison of different methods of wavelet and wavelet packet transform in processing ground motion records. Int. J. Civ. Eng. 7(4), 248\u2013257 (2009)","journal-title":"Int. J. Civ. Eng."},{"issue":"1","key":"1634_CR18","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1121\/1.428310","volume":"107","author":"J Benesty","year":"2000","unstructured":"Benesty, J.: Adaptive eigenvalue decomposition algorithm for passive acoustic source localization. J. Acoust. Soc. Am. 107(1), 384\u2013391 (2000)","journal-title":"J. Acoust. Soc. Am."},{"key":"1634_CR19","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","volume":"20","author":"JR Peter","year":"1987","unstructured":"Peter, J.R.: Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J. Comput. Appl. Math. 20, 53\u201365 (1987)","journal-title":"J. Comput. Appl. Math."},{"key":"1634_CR20","unstructured":"Garofolo, J.S., Lamel, L.F., Fisher, W.M., Fiscus, J.G., Pallett, D.S., Dahlgren, N.L., Zue, V.: TIMIT acoustic-phonetic continuous speech corpus LDC93S1. Web Download. Linguistic Data Consortium, Philadelphia. https:\/\/catalog.ldc.upenn.edu\/LDC93S1. Accessed 20 May 2019"},{"key":"1634_CR21","doi-asserted-by":"crossref","unstructured":"Cetin, O., Shriberg, E.: Analysis of overlaps in meetings by dialog factors, hot spots, speakers, and collection site: insights for automatic speech recognition. In: Proceedings of Interspeech, pp. 293\u2013296 (2006)","DOI":"10.1007\/11965152_19"},{"issue":"4","key":"1634_CR22","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1121\/1.382599","volume":"65","author":"J Allen","year":"1979","unstructured":"Allen, J., Berkley, D.: Image method for efficiently simulating small-room acoustics. J. Acoust. Soc. Am. 65(4), 943\u2013950 (1979)","journal-title":"J. Acoust. Soc. Am."}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-020-01634-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11760-020-01634-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-020-01634-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T15:31:50Z","timestamp":1665675110000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11760-020-01634-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,30]]},"references-count":22,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2020,7]]}},"alternative-id":["1634"],"URL":"https:\/\/doi.org\/10.1007\/s11760-020-01634-2","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2020,1,30]]},"assertion":[{"value":"28 May 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 November 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 November 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 January 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}