{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:43:27Z","timestamp":1760132607984,"version":"3.37.3"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,1,3]],"date-time":"2021-01-03T00:00:00Z","timestamp":1609632000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,3]],"date-time":"2021-01-03T00:00:00Z","timestamp":1609632000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100004541","name":"Ministry of Human Resource Development","doi-asserted-by":"publisher","award":["IMPRINT, 6406"],"award-info":[{"award-number":["IMPRINT, 6406"]}],"id":[{"id":"10.13039\/501100004541","id-type":"DOI","asserted-by":"publisher"}]},{"name":"EUs H2020 research and innovation programme","award":["ENRICH Network: MSCA GA 67532"],"award-info":[{"award-number":["ENRICH Network: MSCA GA 67532"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1007\/s10772-020-09785-w","type":"journal-article","created":{"date-parts":[[2021,1,3]],"date-time":"2021-01-03T06:02:38Z","timestamp":1609653758000},"page":"193-203","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Speech frame selection for spoofing detection with an application to partially spoofed audio-data"],"prefix":"10.1007","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0616-7608","authenticated-orcid":false,"given":"A Kishore","family":"Kumar","sequence":"first","affiliation":[]},{"given":"Dipjyoti","family":"Paul","sequence":"additional","affiliation":[]},{"given":"Monisankha","family":"Pal","sequence":"additional","affiliation":[]},{"given":"Md","family":"Sahidullah","sequence":"additional","affiliation":[]},{"given":"Goutam","family":"Saha","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,1,3]]},"reference":[{"key":"9785_CR1","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":"5","key":"9785_CR2","doi-asserted-by":"publisher","first-page":"922","DOI":"10.1109\/TASL.2009.2038663","volume":"18","author":"D Erro","year":"2010","unstructured":"Erro, D., Moreno, A., & Bonafonte, A. (2010). Voice conversion based on weighted frequency warping. IEEE Transactions on Audio, Speech, and Language Processing, 18(5), 922\u2013931.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"3","key":"9785_CR3","doi-asserted-by":"publisher","first-page":"638","DOI":"10.1109\/TASL.2010.2041386","volume":"18","author":"H Fujihara","year":"2010","unstructured":"Fujihara, H., Goto, M., Kitahara, T., & Okuno, H. G. (2010). A modeling of singing voice robust to accompaniment sounds and its application to singer identification and vocal-timbre-similarity-based music information retrieval. IEEE Transactions on Audio, Speech, and Language Processing, 18(3), 638\u2013648.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9785_CR4","doi-asserted-by":"crossref","unstructured":"Hanil\u00e7i, C., Kinnunen, T., Sahidullah, M., Sizov, A.(2015). Classifiers for synthetic speech detection: A comparison. In Proceeding of the INTERSPEECH, pp. 2057\u20132061","DOI":"10.21437\/Interspeech.2015-466"},{"key":"9785_CR5","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.dsp.2014.08.008","volume":"35","author":"C Hanil\u00e7i","year":"2014","unstructured":"Hanil\u00e7i, C., & Kinnunen, T. (2014). Source cell-phone recognition from recorded speech using non-speech segments. Digital Signal Processing, 35, 75\u201385.","journal-title":"Digital Signal Processing"},{"key":"9785_CR6","unstructured":"Jahangir, M. J., Kenny, P., Bhattacharya, G., Stafylakis, T., & Development of CRIM System for the Automatic Speaker Verification Spoofing and Countermeasures Challenge,. (2015). in Proceeding of the INTERSPEECH, 2015, pp. 2072\u20132076."},{"issue":"6","key":"9785_CR7","doi-asserted-by":"publisher","first-page":"1332","DOI":"10.1109\/TASL.2009.2033631","volume":"18","author":"CS Jung","year":"2010","unstructured":"Jung, C. S., Kim, M. Y., & Kang, H. G. (2010). Selecting feature frames for automatic speaker recognition using mutual information. IEEE Transactions on Audio, Speech, and Language Processing, 18(6), 1332\u20131340.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9785_CR8","doi-asserted-by":"crossref","unstructured":"Kamble, M. R., Sailor, H. B., Patil, H. A., & Li, H. (2020). Advances in anti-spoofing: from the perspective of ASVspoof challenges. APSIPA Transactions on Signal and Information Processing, 9,","DOI":"10.1017\/ATSIP.2019.21"},{"key":"9785_CR9","unstructured":"Khodabakhsh, A., Demiroglu, C. (2016). Investigation of synthetic speech detection using frame-and segment-specific importance weighting. arXiv preprint arXiv:1610.03009"},{"key":"9785_CR10","doi-asserted-by":"crossref","unstructured":"Kinnunen, T., Sahidullah, M., Delgado, H., Todisco, M., Evans, N., Yamagishi, J., Lee, K.A. (2017a). The ASVspoof 2017 challenge: Assessing the limits of replay spoofing attack detection, in Proceeding of the INTERSPEECH, pp. 2\u20136","DOI":"10.21437\/Interspeech.2017-1111"},{"key":"9785_CR11","doi-asserted-by":"crossref","unstructured":"Kinnunen, T., Sahidullah, M., Delgado, H., Todisco, M., Evans, N., Yamagishi, J., Lee, K.A. (2017b). The ASVspoof 2017 challenge: Assessing the limits of replay spoofing attack detection","DOI":"10.21437\/Interspeech.2017-1111"},{"issue":"1","key":"9785_CR12","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1109\/TSA.2005.853206","volume":"14","author":"T Kinnunen","year":"2006","unstructured":"Kinnunen, T., Karpov, E., & Franti, P. (2006). Real-time speaker identification and verification. IEEE Transactions on Audio, Speech, and Language Processing, 14(1), 277\u2013288.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"1","key":"9785_CR13","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.patrec.2006.06.009","volume":"28","author":"S Kwon","year":"2007","unstructured":"Kwon, S., & Narayanan, S. (2007). Robust speaker identification based on selective use of feature vectors. Pattern Recognition Letters, 28(1), 85\u201389.","journal-title":"Pattern Recognition Letters"},{"key":"9785_CR14","unstructured":"Okabe, K., Koshinaka, T., Shinoda, K. (2018). Attentive statistics pooling for deep speaker embedding, in Proceeding of the INTERSPEECH, pp. 2252\u20132256"},{"key":"9785_CR15","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/j.csl.2017.10.001","volume":"48","author":"M Pal","year":"2018","unstructured":"Pal, M., Paul, D., & Saha, G. (2018). Synthetic speech detection using fundamental frequency variation and spectral features. Computer Speech & Language, 48, 31\u201350.","journal-title":"Computer Speech & Language"},{"issue":"4","key":"9785_CR16","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1109\/JSTSP.2016.2647201","volume":"11","author":"TB Patel","year":"2017","unstructured":"Patel, T. B., & Patil, H. A. (2017). Cochlear filter and instantaneous frequency based features for spoofed speech detection. IEEE Journal of Selected Topics in Signal Processing, 11(4), 618\u2013631.","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"9785_CR17","doi-asserted-by":"crossref","unstructured":"Paul, D., Sahidullah, M., Saha, G. (2017b). Generalization of spoofing countermeasures: A case study with ASVspoof 2015 and BTAS 2016 corpora, in Proceeding of the ICASSP, pp. 2047\u20132051","DOI":"10.1109\/ICASSP.2017.7952516"},{"issue":"4","key":"9785_CR18","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1109\/JSTSP.2017.2684705","volume":"11","author":"D Paul","year":"2017","unstructured":"Paul, D., Pal, M., & Saha, G. (2017a). Spectral features for synthetic speech detection. IEEE Journal of Selected Topics in Signal Processing, 11(4), 605\u2013617.","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"issue":"1","key":"9785_CR19","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1109\/89.365379","volume":"3","author":"DA Reynolds","year":"1995","unstructured":"Reynolds, D. A., & Rose, R. C. (1995). Robust text-independent speaker identification using Gaussian mixture speaker models. IEEE Transactions on Speech and Audio Processing, 3(1), 72\u201383.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9785_CR20","unstructured":"Sahidullah, M., Delgado, H., Todisco, M., Kinnunen, T., Evans, N., Yamagishi, J., Lee, K.-A.(2019) .Introduction to Voice Presentation Attack Detection and Recent Advances, ed. by S. Marcel, M.S. Nixon, J. Fierrez, N. Evans (Springer, Cham), pp. 321\u2013361"},{"key":"9785_CR21","unstructured":"Sahidullah, M., Kinnunen, T., Hanil\u00e7i, C. (2015). A comparison of features for synthetic speech detection, in Proceeding of the INTERSPEECH, pp. 2087\u20132091"},{"issue":"4","key":"9785_CR22","doi-asserted-by":"publisher","first-page":"810","DOI":"10.1109\/TIFS.2015.2398812","volume":"10","author":"J Sanchez","year":"2015","unstructured":"Sanchez, J., Saratxaga, I., Hernaez, I., Navas, E., Erro, D., & Raitio, T. (2015). Toward a universal synthetic speech spoofing detection using phase information. IEEE Transactions on Information Forensics and Security, 10(4), 810\u2013820.","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"9785_CR23","unstructured":"Tian, X., Xiao, X., Chng, E.S., Li, H. (2016). Spoofing speech detection using temporal convolutional neural network, in ASIPA, pp. 1\u20136"},{"key":"9785_CR24","doi-asserted-by":"crossref","unstructured":"Todisco, M., Wang, X., Vestman, V., Sahidullah, M., Delgado, H., Nautsch, A., Yamagishi, J., Evans, N., Kinnunen, T., Lee, K.A. (2019). Asvspoof 2019: Future horizons in spoofed and fake audio detection. arXiv preprint arXiv:1904.05441","DOI":"10.21437\/Interspeech.2019-2249"},{"key":"9785_CR25","doi-asserted-by":"publisher","first-page":"516","DOI":"10.1016\/j.csl.2017.01.001","volume":"45","author":"M Todisco","year":"2017","unstructured":"Todisco, M., Delgado, H., & Evans, N. (2017). Constant Q cepstral coefficients: A spoofing countermeasure for automatic speaker verification. Computer Speech & Language, 45, 516\u2013535.","journal-title":"Computer Speech & Language"},{"key":"9785_CR26","unstructured":"Tom, F., Jain, M., Dey, P.(2018). End-To-end audio replay attack detection using deep convolutional networks with attention, in Proceeding of the INTERSPEECH, pp. 681\u2013685"},{"issue":"22","key":"9785_CR27","doi-asserted-by":"publisher","first-page":"8463","DOI":"10.1016\/j.eswa.2015.07.002","volume":"42","author":"TM Ventura","year":"2015","unstructured":"Ventura, T. M., de Oliveira, A. G., Ganchev, T. D., de Figueiredo, J. M., Jahn, O., Marques, M. I., et al. (2015). Audio parameterization with robust frame selection for improved bird identification. Expert Systems with Applications, 42(22), 8463\u20138471.","journal-title":"Expert Systems with Applications"},{"key":"9785_CR28","doi-asserted-by":"crossref","unstructured":"Villalba, J.A., Miguel, A., Ortega, A., Lleida, E. (2015a). Spoofing detection with DNN and one-class SVM for the ASVspoof 2015 challenge, in Proceeding of the INTERSPEECH, pp. 2067\u20132071","DOI":"10.21437\/Interspeech.2015-468"},{"key":"9785_CR29","doi-asserted-by":"crossref","unstructured":"Villalba, J., Miguel, A., Ortega, A., Lleida, E. (2015b). Spoofing detection with dnn and one-class svm for the asv spoof 2015 challenge, in Proceeding of the INTERSPEECH","DOI":"10.21437\/Interspeech.2015-468"},{"key":"9785_CR30","doi-asserted-by":"crossref","unstructured":"Wu, Z., Kinnunen, T., Evans, N., Yamagishi, J., Hanil\u00e7i, C., Sahidullah, M., Sizov, A.(2015). ASVspoof 2015: The first automatic speaker verification spoofing and countermeasures challenge, in Proceeding of the INTERSPEECH, 2037\u20132041","DOI":"10.21437\/Interspeech.2015-462"},{"issue":"4","key":"9785_CR31","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1109\/JSTSP.2017.2671435","volume":"11","author":"Z Wu","year":"2017","unstructured":"Wu, Z., et al. (2017). ASVspoof: the automatic speaker verification spoofing and countermeasures challenge. IEEE Journal of Selected Topics in Signal Processing, 11(4), 588\u2013604.","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"9785_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 countermeasures for speaker verification: A survey. Speech Communication, 66, 130\u2013153.","journal-title":"Speech Communication"},{"issue":"10","key":"9785_CR33","doi-asserted-by":"publisher","first-page":"4633","DOI":"10.1109\/TNNLS.2017.2771947","volume":"29","author":"H Yu","year":"2017","unstructured":"Yu, H., Tan, Z.-H., Ma, Z., Martin, R., & Guo, J. (2017). Spoofing detection in automatic speaker verification systems using DNN classifiers and dynamic acoustic features. IEEE Transactions on Neural Networks and Learning Systems, 29(10), 4633\u20134644.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"9785_CR34","unstructured":"Zhu, Y., Ko, T., Snyder, D., Mak, B., Povey, D. (2018). Self-attentive speaker embeddings for text-independent speaker verification, in Proceeding of the INTERSPEECH, pp. 3573\u20133577"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-020-09785-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-020-09785-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-020-09785-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,10]],"date-time":"2022-12-10T08:17:13Z","timestamp":1670660233000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-020-09785-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,3]]},"references-count":34,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,3]]}},"alternative-id":["9785"],"URL":"https:\/\/doi.org\/10.1007\/s10772-020-09785-w","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2021,1,3]]},"assertion":[{"value":"14 March 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 November 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}