{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T17:08:52Z","timestamp":1773248932582,"version":"3.50.1"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2012,6,27]],"date-time":"2012-06-27T00:00:00Z","timestamp":1340755200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2012,9]]},"DOI":"10.1007\/s10772-012-9163-3","type":"journal-article","created":{"date-parts":[[2012,6,27]],"date-time":"2012-06-27T13:54:59Z","timestamp":1340805299000},"page":"407-417","source":"Crossref","is-referenced-by-count":14,"title":["Analysis and detection of mimicked speech based on prosodic features"],"prefix":"10.1007","volume":"15","author":[{"given":"Leena","family":"Mary","sequence":"first","affiliation":[]},{"given":"K. K.","family":"Anish Babu","sequence":"additional","affiliation":[]},{"given":"Aju","family":"Joseph","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2012,6,27]]},"reference":[{"key":"9163_CR1","first-page":"788","volume-title":"Proceeding of int. conf. acoust., speech and signal processing","author":"A. G. Adami","year":"2003","unstructured":"Adami, A. G., Mihaescu, R., Reynolds, D. A., & Godfrey, J. J. (2003). Modeling prosodic dynamics for speaker recognition. In Proceeding of int. conf. acoust., speech and signal processing, Hong Kong, China (Vol.\u00a04, pp. 788\u2013791)."},{"issue":"3","key":"9163_CR2","doi-asserted-by":"crossref","first-page":"1687","DOI":"10.1121\/1.1913303","volume":"52","author":"B. Atal","year":"1972","unstructured":"Atal, B. (1972). Automatic speaker recognition based on pitch contours. The Journal of the Acoustical Society of America, 52(3), 1687\u20131697.","journal-title":"The Journal of the Acoustical Society of America"},{"key":"9163_CR3","first-page":"84","volume-title":"Proceedings FONETIK 2004 the XVIIth Swedish phonetics conference","author":"M. Blomberg","year":"2004","unstructured":"Blomberg, M., Elenius, D., & Zetterholm, E. (2004). Speaker verification scores and acoustic analysis of a professional impersonator. In Proceedings FONETIK 2004 the XVIIth Swedish phonetics conference (pp. 84\u201387)."},{"issue":"9","key":"9163_CR4","doi-asserted-by":"crossref","first-page":"1437","DOI":"10.1109\/5.628714","volume":"85","author":"J. P. Campbell","year":"1997","unstructured":"Campbell, J. P. (1997). Speaker recognition: A tutorial. Proceedings of the IEEE, 85(9), 1437\u20131462.","journal-title":"Proceedings of the IEEE"},{"key":"9163_CR5","doi-asserted-by":"crossref","unstructured":"Drygajlo, A. (2007). Forensic automatic speaker recognition. IEEE Signal Processing Magazine, 132\u2013135.","DOI":"10.1109\/MSP.2007.323278"},{"issue":"1","key":"9163_CR6","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1558\/ijsll.v17i1.119","volume":"17","author":"M. Farr\u00fas","year":"2010","unstructured":"Farr\u00fas, M., Wagner, M., Erro, D., & Hernando, J. (2010). Automatic speaker recognition as a measurement of voice imitation and conversion. The International Journal of Speech, Language and the Law, 17(1), 119\u2013142.","journal-title":"The International Journal of Speech, Language and the Law"},{"key":"9163_CR7","unstructured":"Heck, L. P. (2002). Integrating high-level information for robust speaker recognition in John Hopkins University workshop on SuperSID. Baltimore, Maryland. http:\/\/www.cslp.jhu.edu\/ws2002\/groups\/supersid ."},{"key":"9163_CR8","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.specom.2009.08.009","volume":"52","author":"T. Kinnunen","year":"2010","unstructured":"Kinnunen, T., & Li, H. (2010). An overview of text-independent speaker recognition: from features to supervectors. Speech Communication, 52, 12\u201340.","journal-title":"Speech Communication"},{"key":"9163_CR9","first-page":"601","volume-title":"Proceedings of int. conf. acoust., speech and signal processing","author":"C. Lin","year":"2005","unstructured":"Lin, C., & Wang, H. (2005). Language identification using pitch contour information. In Proceedings of int. conf. acoust., speech and signal processing, Philadelphia. USA (Vol.\u00a0I, pp. 601\u2013605)."},{"key":"9163_CR10","unstructured":"Mary, L. (2006). Multilevel implicit features for language and speaker recognition. Ph.D. Thesis, Indian Institute of Technology, Madras, India."},{"key":"9163_CR11","first-page":"365","volume-title":"Forensic speaker recognition\u2014law enforcement and counter-terrorism","author":"L. Mary","year":"2011","unstructured":"Mary, L. (2011). Prosodic features for speaker recognition. In A.\u00a0Neustein & H.\u00a0A.\u00a0Patil (Eds.), Forensic speaker recognition\u2014law enforcement and counter-terrorism (pp. 365\u2013388). Berlin: Springer."},{"key":"9163_CR12","first-page":"917","volume-title":"Proceedings of interspeech","author":"L. Mary","year":"2006","unstructured":"Mary, L., & Yegnanarayana, B. (2006). Prosodic features for speaker verification. In Proceedings of interspeech, Pittsburgh, Pennsylvania (pp. 917\u2013920)."},{"key":"9163_CR13","doi-asserted-by":"crossref","first-page":"782","DOI":"10.1016\/j.specom.2008.04.010","volume":"50","author":"L. Mary","year":"2008","unstructured":"Mary, L., & Yegnanarayana, B. (2008). Extraction and representation of prosodic features for language and speaker recognition. Speech Communication, 50, 782\u2013796.","journal-title":"Speech Communication"},{"key":"9163_CR14","first-page":"4478","volume-title":"Proceeding of int. conf. acoust., speech and signal processing","author":"M. H. Moattar","year":"2010","unstructured":"Moattar, M. H., Homayounpour, M. M., & Kalantari, N. K. (2010). A\u00a0new approach for robust realtime voice activity detection using spectral pattern. In Proceeding of int. conf. acoust., speech and signal processing (pp. 4478\u20134481)."},{"key":"9163_CR15","unstructured":"NIST (2001). Speaker recognition evaluation website. http:\/\/www.nist.gov\/speech\/tests\/spk\/2001 ."},{"key":"9163_CR16","first-page":"5681","volume-title":"Proceedings of acoustics 08","author":"P. Perrot","year":"2008","unstructured":"Perrot, P., & Chollet, G. (2008). The question of disguised voice. In Proceedings of acoustics 08, Paris (pp. 5681\u20135685)."},{"key":"9163_CR17","series-title":"Lecture notes in computer science.","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1007\/978-3-540-71505-4_7","volume-title":"Progress in nonlinear speech processing","author":"P. Perrot","year":"2007","unstructured":"Perrot, P., Aversano, G., & Chollet, G. (2007). Voice disguise and automatic detection: review and perspectives. Lecture notes in computer science.: Vol.\u00a04391. In Progress in nonlinear speech processing (pp. 101\u2013117). Berlin: Springer."},{"key":"9163_CR18","series-title":"Lecture notes of the Institute for Computer Sciences","first-page":"179","volume-title":"Vocal forgery in forensic sciences, Social Informatics and Telecommunication Engineering","author":"P. Perrot","year":"2009","unstructured":"Perrot, P., Morel, M., Razik, G., & Chollet, G. (2009). Lecture notes of the Institute for Computer Sciences: Vol. 8. Vocal forgery in forensic sciences, Social Informatics and Telecommunication Engineering (pp. 179\u2013185). Berlin: Springer."},{"issue":"1\u20132","key":"9163_CR19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2000000001","volume":"1","author":"L. R. Rabinerl","year":"2007","unstructured":"Rabinerl, L. R., & Schafer, R. W. (2007). Introduction to digital speech processing. Foundations and Trends in Signal Processing, 1(1\u20132), 1\u2013194.","journal-title":"Foundations and Trends in Signal Processing"},{"key":"9163_CR20","first-page":"784","volume-title":"Proceedings of int. conf. acoust., speech and signal processing","author":"D. Reynolds","year":"2003","unstructured":"Reynolds, D., Andrews, W., Campbell, J., Navratil, J., Peskin, B., Adami, A., Jin, Q., Klusacek, D., Abramson, J., Mihaescu, R., Godfrey, J., Jones, D., & Xiang, B. (2003). The superSID project: exploiting high-level information for high-accuracy speaker recognition. In Proceedings of int. conf. acoust., speech and signal processing, Hong Kong, China (Vol.\u00a04, pp. 784\u2013787)."},{"key":"9163_CR21","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.csl.2005.07.003","volume":"20","author":"P. Rose","year":"2006","unstructured":"Rose, P. (2006). Technical speaker recognition: evaluation, types and testing of evidence. Computer Speech & Language, 20, 159\u2013191.","journal-title":"Computer Speech & Language"},{"key":"9163_CR22","doi-asserted-by":"crossref","first-page":"1509","DOI":"10.21437\/Interspeech.2008-433","volume-title":"Proceedings of interspeech","author":"E. Shriberg","year":"2008","unstructured":"Shriberg, E., & Stolcke (2008). The case for automatic higher level features in forensic speaker recognition. In Proceedings of interspeech (pp. 1509\u20131512)."},{"key":"9163_CR23","doi-asserted-by":"crossref","first-page":"1509","DOI":"10.21437\/Interspeech.2008-433","volume-title":"Proceedings of interspeech","author":"E. Shriberg","year":"2008","unstructured":"Shriberg, E., & Stolcke (2008). The case for automatic higher level features in forensic speaker recognition. In Proceedings of interspeech (pp. 1509\u20131512)."},{"key":"9163_CR24","first-page":"70","volume-title":"Proceedings of the 11th Australian international conference on speech science and technology","author":"E. Zetterholm","year":"2006","unstructured":"Zetterholm, E. (2006). Same speaker\u2013different voices. A\u00a0study of one impersonator and some of his different imitations. In Proceedings of the 11th Australian international conference on speech science and technology (pp. 70\u201375)."},{"key":"9163_CR25","first-page":"291","volume-title":"Proceedings of the 9th Australian conference on speech science and technology","author":"E. Zetterholm","year":"2002","unstructured":"Zetterholm, E., & Sullivan, K. P. H. (2002). The impact of semantic expectation on the acceptance of a voice imitation. In Proceedings of the 9th Australian conference on speech science and technology (pp. 291\u2013296)."},{"key":"9163_CR26","first-page":"393","volume-title":"Proceedings of the 10th Australian international conference on speech science and technology","author":"E. Zetterholm","year":"2004","unstructured":"Zetterholm, E., Blomberg, M., & Elenius, D. A. (2004). Comparison between human perception and a speaker verification system score of a voice imitation. In Proceedings of the 10th Australian international conference on speech science and technology (pp. 393\u2013397)."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-012-9163-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-012-9163-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-012-9163-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,19]],"date-time":"2022-01-19T16:43:28Z","timestamp":1642610608000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-012-9163-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,6,27]]},"references-count":26,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2012,9]]}},"alternative-id":["9163"],"URL":"https:\/\/doi.org\/10.1007\/s10772-012-9163-3","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,6,27]]}}}