{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:55:48Z","timestamp":1764784548161,"version":"3.37.3"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2021,2,4]],"date-time":"2021-02-04T00:00:00Z","timestamp":1612396800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,2,4]],"date-time":"2021-02-04T00:00:00Z","timestamp":1612396800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100008628","name":"Ministry of Electronics and Information technology","doi-asserted-by":"publisher","award":["12(5)\/2015-ESD"],"award-info":[{"award-number":["12(5)\/2015-ESD"]}],"id":[{"id":"10.13039\/501100008628","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1007\/s10772-021-09810-6","type":"journal-article","created":{"date-parts":[[2021,2,4]],"date-time":"2021-02-04T08:04:06Z","timestamp":1612425846000},"page":"497-507","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Detection of replay signals using excitation source and shifted CQCC features"],"prefix":"10.1007","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9740-6987","authenticated-orcid":false,"given":"Krishna","family":"Dutta","sequence":"first","affiliation":[]},{"given":"Madhusudan","family":"Singh","sequence":"additional","affiliation":[]},{"given":"Debadatta","family":"Pati","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,2,4]]},"reference":[{"key":"9810_CR1","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/0167-6393(92)90005-R","volume":"11","author":"P Alku","year":"1991","unstructured":"Alku, P. (1991). Glottal wave analysis with pitch synchronous iterative adaptive inverse filtering. Speech Communication, 11, 109\u2013118.","journal-title":"Speech Communication"},{"key":"9810_CR2","doi-asserted-by":"crossref","unstructured":"Beigi, H. (2011). Speaker recognition. In: Fundamentals of Speaker Recognition (pp.\u00a0543\u2013559). New York: Springer.","DOI":"10.1007\/978-0-387-77592-0_17"},{"issue":"9","key":"9810_CR3","doi-asserted-by":"publisher","first-page":"1437","DOI":"10.1109\/5.628714","volume":"85","author":"JP Campbell","year":"1997","unstructured":"Campbell, J. P. (1997). Speaker recognition: A tutorial. Proceedings of IEEE, 85(9), 1437\u20131462.","journal-title":"Proceedings of IEEE"},{"key":"9810_CR4","doi-asserted-by":"crossref","unstructured":"Delgado, H., Todisco, M., Sahidullah, M., Evans, N., Kinnunen, T., Lee, K., Yamagishi, J. (2018). Asvspoof 2017 version 2.0: meta-data analysis and baseline enhancements. In Odyssey 2018 The Speaker and Language Recognition Workshop.","DOI":"10.21437\/Odyssey.2018-42"},{"issue":"3","key":"9810_CR5","doi-asserted-by":"publisher","first-page":"994","DOI":"10.1109\/TASL.2011.2170835","volume":"20","author":"T Drugman","year":"2012","unstructured":"Drugman, T., Thomas, M., Gudnason, J., Naylor, P., & Dutoit, T. (2012). Detection of glottal closure instants from speech signals: A quantitative review. IEEE Transactions on Audio, Speech, and Language Processing, 20(3), 994\u20131006.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9810_CR6","doi-asserted-by":"crossref","unstructured":"Font, R., Esp\u0131n, J. M., & Cano, M. J. (2017). Experimental analysis of features for replay attack detection\u2013results on the ASVspoof 2017 challenge. in Proc Interspeech pp. 7\u201311.","DOI":"10.21437\/Interspeech.2017-450"},{"issue":"2","key":"9810_CR7","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1109\/TASSP.1981.1163530","volume":"29","author":"S Furui","year":"1981","unstructured":"Furui, S. (1981). Cepstral analysis technique for automatic speaker verification. IEEE Transactions on Acoustics, Speech, and Signal Processing, 29(2), 254\u2013272.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"issue":"4","key":"9810_CR8","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1109\/89.326616","volume":"2","author":"H Hermansky","year":"1994","unstructured":"Hermansky, H., & Morgan, N. (1994). Rasta processing of speech. IEEE Transactions on Speech and Audio Processing, 2(4), 578\u2013589.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9810_CR9","doi-asserted-by":"crossref","unstructured":"Jelil, S., Das, R. K., Prasanna, S. M., & Sinha, R. (2017). Spoof detection using source, instantaneous frequency and cepstral features. In Proc Interspeech (pp.\u00a022\u201326).","DOI":"10.21437\/Interspeech.2017-930"},{"key":"9810_CR10","doi-asserted-by":"crossref","unstructured":"Kamble, M., & Patil, H. (2018). Novel variable length energy separation algorithm using instantaneous amplitude features for replay detection. Proc. Interspeech, 2018, pp.\u00a0646\u2013650.","DOI":"10.21437\/Interspeech.2018-1687"},{"issue":"1508","key":"9810_CR11","first-page":"1508","volume":"10","author":"T Kinnunen","year":"2017","unstructured":"Kinnunen, T., Evans, N., Yamagishi, J., Lee, K. A., Sahidullah, M., Todisco, M., et al. (2017). Asvspoof 2017: Automatic speaker verification spoofing and countermeasures challenge evaluation plan. Training, 10(1508), 1508.","journal-title":"Training"},{"key":"9810_CR12","doi-asserted-by":"crossref","unstructured":"Lee, K. A., Larcher, A., Wang, G., Kenny, P., Br\u00fcmmer, N., Leeuwen, D. v., et\u00a0al. (2015). The reddots data collection for speaker recognition. In Sixteenth Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2015-95"},{"key":"9810_CR13","doi-asserted-by":"crossref","unstructured":"Martin, A., Doddington, G., Kamm, T., Ordowski, M., & Przybocki, M. (1997). The DET curve in assessment of detection task performance. In: Proc. Eur. conf. on speech communication technology, Rhodes, Greece, Vol.\u00a04, pp. 1895\u20131898.","DOI":"10.21437\/Eurospeech.1997-504"},{"issue":"8","key":"9810_CR14","doi-asserted-by":"publisher","first-page":"1602","DOI":"10.1109\/TASL.2008.2004526","volume":"16","author":"KSR Murthy","year":"2008","unstructured":"Murthy, K. S. R., & Yegnanarayana, B. (2008). Epoch extraction from speech signals. IEEE Transactions on Audio Speech and Language Processing, 16(8), 1602\u20131613.","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"issue":"1","key":"9810_CR15","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/TASL.2006.876878","volume":"15","author":"PA Naylor","year":"2007","unstructured":"Naylor, P. A., Kounoudes, A., Gudnason, J., & Brookes, M. (2007). Estimation of glottal closure instants in voiced speech using the DYPSA algorithm. IEEE Transactions on Audio, Speech, and Language Processing, 15(1), 34\u201343.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9810_CR16","first-page":"717","volume":"2","author":"F Nordin","year":"2001","unstructured":"Nordin, F., & Eriksson, T. (2001). A speech spectrum distortion measure with interframe memory. Proc. ICASSP, 2, 717\u2013720.","journal-title":"Proc. ICASSP"},{"key":"9810_CR17","doi-asserted-by":"crossref","unstructured":"Patil, H. A., Kamble, M. R., Patel, T. B., & Soni, M. (2017). Novel variable length teager energy separation based instantaneous frequency features for replay detection. In Proc Interspeech (pp.\u00a012\u201316).","DOI":"10.21437\/Interspeech.2017-1362"},{"issue":"5","key":"9810_CR18","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1109\/89.784109","volume":"7","author":"MD Plumpe","year":"1999","unstructured":"Plumpe, M. D., Quatieri, T. F., & Reynolds, D. A. (1999). Modelling of glottal flow derivative waveform with application to speaker identification. IEEE Transactions on Speech and Audio Processing, 7(5), 569\u2013586.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9810_CR19","doi-asserted-by":"publisher","first-page":"1243","DOI":"10.1016\/j.specom.2006.06.002","volume":"48","author":"SRM Prasanna","year":"2006","unstructured":"Prasanna, S. R. M., Gupta, C. S., & Yegnanarayana, B. (2006a). Extraction of speaker-specific excitation information from linear prediction residual of speech. Speech Communication, 48, 1243\u20131261.","journal-title":"Speech Communication"},{"key":"9810_CR20","doi-asserted-by":"publisher","first-page":"1243","DOI":"10.1016\/j.specom.2006.06.002","volume":"48","author":"SRM Prasanna","year":"2006","unstructured":"Prasanna, S. R. M., Gupta, C. S., & Yegnanarayana, B. (2006b). Extraction of speaker-specific excitation information from linear prediction residual of speech. Speech Communication, 48, 1243\u20131261.","journal-title":"Speech Communication"},{"issue":"12","key":"9810_CR21","doi-asserted-by":"publisher","first-page":"2471","DOI":"10.1109\/TASL.2013.2273717","volume":"21","author":"A Prathosh","year":"2013","unstructured":"Prathosh, A., Ananthapadmanabha, T., & Ramakrishnan, A. (2013). Epoch extraction based on integrated linear prediction residual using plosion index. IEEE Transactions on Audio, Speech, and Language Processing, 21(12), 2471\u20132480.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9810_CR22","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/0167-6393(95)00009-D","volume":"17","author":"DA Reynolds","year":"1995","unstructured":"Reynolds, D. A. (1995). Speaker identification and verification using gaussian mixture speaker models. Speech Communication, 17, 91\u2013108.","journal-title":"Speech Communication"},{"key":"9810_CR23","doi-asserted-by":"crossref","unstructured":"Sailor, H., Kamble, M., Patil, H. (2018). Auditory filterbank learning for temporal modulation features in replay spoof speech detection. In Proc. Interspeech, pp. 666\u2013670.","DOI":"10.21437\/Interspeech.2018-1651"},{"key":"9810_CR24","doi-asserted-by":"publisher","unstructured":"Singh, M., & Pati, D. (2019). Usefulness of linear prediction residual for replay attack detection. AEU-International Journal of Electronics and Communications. https:\/\/doi.org\/10.1016\/j.aeue.2019.152837.","DOI":"10.1016\/j.aeue.2019.152837"},{"key":"9810_CR25","doi-asserted-by":"crossref","unstructured":"Suthokumar, G., Sethu, V., Wijenayake, C., Ambikairajah, E. (2018). Modulation dynamic features for the detection of replay attacks. Proc Interspeech pp. 691\u2013695.","DOI":"10.21437\/Interspeech.2018-1846"},{"key":"9810_CR26","doi-asserted-by":"publisher","first-page":"726","DOI":"10.21437\/Interspeech.2018-1702","volume":"2018","author":"H Tak","year":"2018","unstructured":"Tak, H., & Patil, H. (2018). Novel linear frequency residual cepstral features for replay attack detection. Proc. Interspeech, 2018, 726\u2013730.","journal-title":"Proc. Interspeech"},{"key":"9810_CR27","unstructured":"The Bosaris toolkit [software package]. Retrieved 2013 from https:\/\/sites.google.com\/site\/bosaristoolkit."},{"issue":"1","key":"9810_CR28","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/TASL.2011.2157684","volume":"20","author":"MR Thomas","year":"2012","unstructured":"Thomas, M. R., Gudnason, J., & Naylor, P. A. (2012). Estimation of glottal closing and opening instants in voiced speech using the YAGA algorithm. IEEE Transactions on Audio, Speech, and Language Processing, 20(1), 82\u201391.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9810_CR29","doi-asserted-by":"crossref","unstructured":"Torres-Carrasquillo, P. A., Singer, E., Kohler, M. A., Greene, R. J., Reynolds, D. A., & Deller,\u00a0Jr J.R. (2002). Approaches to language identification using gaussian mixture models and shifted delta cepstral features. In Seventh International Conference on Spoken Language Processing.","DOI":"10.1109\/ICASSP.2002.5743828"},{"key":"9810_CR30","doi-asserted-by":"crossref","unstructured":"Villaba, J., Lieida, E. (2011). Preventing replay attacks on speaker verification systems. In Proc. Int. carnahan conf. on security technology (ICCST), pp. 1\u20138.","DOI":"10.1109\/CCST.2011.6095943"},{"key":"9810_CR31","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wei, G., He, Q.H. (2011). Channel pattern noise based playback attack detection algorithm for speaker recognition. in Proc IEEE Int conference of the biometrics special interest Group (BIOSIG) on machine learning and cybernetics pp 1708\u20131713.","DOI":"10.1109\/ICMLC.2011.6016982"},{"key":"9810_CR32","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1016\/j.specom.2014.10.005","volume":"66","author":"Z Wu","year":"2015","unstructured":"Wu, Z., Evans, N., Kinnunen, T., Yamagishi, J., Alegre, F., & Li, H. (2015). Spoofing and counter measures for speaker verification: A survey. Speech Communication, 66, 130\u2013153.","journal-title":"Speech Communication"},{"issue":"2","key":"9810_CR33","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1109\/TASL.2010.2047680","volume":"19","author":"WQ Zhang","year":"2010","unstructured":"Zhang, W. Q., He, L., Deng, Y., Liu, J., & Johnson, M. T. (2010). Time-frequency cepstral features and heteroscedastic linear discriminant analysis for language recognition. IEEE Transactions on Audio, Speech, and Language Processing, 19(2), 266\u2013276.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09810-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-021-09810-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09810-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T18:26:31Z","timestamp":1671042391000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-021-09810-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,4]]},"references-count":33,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,6]]}},"alternative-id":["9810"],"URL":"https:\/\/doi.org\/10.1007\/s10772-021-09810-6","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2021,2,4]]},"assertion":[{"value":"31 January 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 January 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 February 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}