{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T02:20:56Z","timestamp":1743042056210,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030878016"},{"type":"electronic","value":"9783030878023"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-87802-3_46","type":"book-chapter","created":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T23:36:52Z","timestamp":1632267412000},"page":"504-515","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Spectral Root Features for Replay Spoof Detection in Voice Assistants"],"prefix":"10.1007","author":[{"given":"Ankur T.","family":"Patil","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harsh","family":"Kotta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajul","family":"Acharya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hemant A.","family":"Patil","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,22]]},"reference":[{"key":"46_CR1","unstructured":"Alegre, F., Janicki, A., Evans, N.: Re-assessing the threat of replay spoofing attacks against automatic speaker verification. In: 2014 International Conference of the Biometrics Special Interest Group (BIOSIG), pp. 1\u20136. IEEE (2014)"},{"key":"46_CR2","doi-asserted-by":"crossref","unstructured":"Cai, W., Wu, H., Cai, D., Li, M.: The DKU replay detection system for the ASVspoof 2019 challenge: on data augmentation, feature representation, classification, and fusion. In: INTERSPEECH, pp. 1023\u20131027, Graz, Austria, September 2019","DOI":"10.21437\/Interspeech.2019-1230"},{"key":"46_CR3","unstructured":"Carlini, N., et al.: Hidden voice commands. In: 25th USENIX Security Symposium, pp. 513\u2013530, Austin, USA, August 2016"},{"key":"46_CR4","doi-asserted-by":"crossref","unstructured":"Carlini, N., Wagner, D.: Audio adversarial examples: targeted attacks on speech-to-text. In: IEEE Security and Privacy Workshops (SPW), pp. 1\u20137, San Francisco, USA, May 2018","DOI":"10.1109\/SPW.2018.00009"},{"key":"46_CR5","doi-asserted-by":"crossref","unstructured":"Delgado, H., et al.: ASVspoof 2017 version 2.0: meta-data analysis and baseline enhancements. In: Odyssey 2018: The Speaker and Language Recognition Workshop, pp. 296\u2013303, Les Sables d\u2019Olonne, France, June 2018","DOI":"10.21437\/Odyssey.2018-42"},{"key":"46_CR6","doi-asserted-by":"crossref","unstructured":"Diao, W., Liu, X., Zhou, Z., Zhang, K.: Your voice assistant is mine: how to abuse speakers to steal information and control your phone. In: 4th ACM Workshop on SPSM, pp. 63\u201374, Scottsdale, USA, November 2014","DOI":"10.1145\/2666620.2666623"},{"key":"46_CR7","unstructured":"Gong, Y., Poellabauer, C.: An overview of vulnerabilities of voice controlled systems. In: $$1^{st}$$ International Workshop on Security and Privacy for Internet-of-Things, Orlando, United States, April 2018"},{"key":"46_CR8","doi-asserted-by":"crossref","unstructured":"Gong, Y., Yang, J., Huber, J., MacKnight, M., Poellabauer, C.: ReMASC: realistic replay attack corpus for voice controlled systems. In: INTERSPEECH, pp. 2355\u20132359, Graz, Austria, September 2019","DOI":"10.21437\/Interspeech.2019-1541"},{"key":"46_CR9","unstructured":"Goodfellow, I.J., Warde-Farley, D., Mirza, M., Courville, A., Bengio, Y.: Maxout networks. In: International Conference on Machine Learning, pp. 1319\u20131327, Atlanta, USA, June 2013"},{"issue":"4","key":"46_CR10","doi-asserted-by":"publisher","first-page":"1738","DOI":"10.1121\/1.399423","volume":"87","author":"H Hermansky","year":"1990","unstructured":"Hermansky, H.: Perceptual linear predictive (PLP) analysis of speech. J. Acoust. Soc. Am. 87(4), 1738\u20131752 (1990)","journal-title":"J. Acoust. Soc. Am."},{"issue":"4","key":"46_CR11","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1109\/89.326616","volume":"2","author":"H Hermansky","year":"1994","unstructured":"Hermansky, H., Morgan, N.: RASTA processing of speech. IEEE Trans. Speech Audio Process. 2(4), 578\u2013589 (1994)","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"7","key":"46_CR12","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.1109\/TASLP.2016.2545928","volume":"24","author":"C Kim","year":"2016","unstructured":"Kim, C., Stern, R.M.: Power-normalized cepstral coefficients (PNCC) for robust speech recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 24(7), 1315\u20131329 (2016)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"46_CR13","doi-asserted-by":"crossref","unstructured":"Lai, C.I., Chen, N., Villalba, J., Dehak, N.: ASSERT: anti-spoofing with squeeze-excitation and residual networks. In: INTERSPEECH, pp. 1013\u20131017, Graz, Austria, September 2019","DOI":"10.21437\/Interspeech.2019-1794"},{"key":"46_CR14","doi-asserted-by":"crossref","unstructured":"Lavrentyeva, G., Novoselov, S., Malykh, E., Kozlov, A., Kudashev, O., Shchemelinin, V.: Audio replay attack detection with deep learning frameworks. In: INTERSPEECH, pp. 82\u201386. Stockholm, Sweden, August 2017","DOI":"10.21437\/Interspeech.2017-360"},{"issue":"3","key":"46_CR15","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1109\/TASSP.1979.1163234","volume":"27","author":"J Lim","year":"1979","unstructured":"Lim, J.: Spectral root homomorphic deconvolution system. IEEE Trans. Acoust. Speech Signal Process. 27(3), 223\u2013233 (1979)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"issue":"4","key":"46_CR16","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1109\/PROC.1975.9792","volume":"63","author":"J Makhoul","year":"1975","unstructured":"Makhoul, J.: Linear prediction: a tutorial review. Proc. IEEE 63(4), 561\u2013580 (1975)","journal-title":"Proc. IEEE"},{"key":"46_CR17","series-title":"Advances in Computer Vision and Pattern Recognition","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-6524-8","volume-title":"Handbook of Biometric Anti-Spoofing","year":"2014","unstructured":"Marcel, S., Nixon, M.S., Li, S.Z. (eds.): Handbook of Biometric Anti-Spoofing. ACVPR, Springer, London (2014). https:\/\/doi.org\/10.1007\/978-1-4471-6524-8"},{"key":"46_CR18","volume-title":"Linear Prediction of Speech","author":"JD Markel","year":"2013","unstructured":"Markel, J.D., Gray, A.J.: Linear Prediction of Speech, vol. 12. Springer, Heidelberg (2013)"},{"issue":"2","key":"46_CR19","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TAU.1968.1161965","volume":"16","author":"A Oppenheim","year":"1968","unstructured":"Oppenheim, A., Schafer, R.: Homomorphic analysis of speech. IEEE Trans. Audio Electroacoust. 16(2), 221\u2013226 (1968). https:\/\/doi.org\/10.1109\/TAU.1968.1161965","journal-title":"IEEE Trans. Audio Electroacoust."},{"key":"46_CR20","unstructured":"Oppenheim, A.V.: Superposition in a class of nonlinear systems. MIT Research Laboratory of Electronics (1965)"},{"issue":"2","key":"46_CR21","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1121\/1.1911395","volume":"45","author":"AV Oppenheim","year":"1969","unstructured":"Oppenheim, A.V.: Speech analysis-synthesis system based on homomorphic filtering. J. Acoust. Soc. Am. (JASA) 45(2), 458\u2013465 (1969)","journal-title":"J. Acoust. Soc. Am. (JASA)"},{"issue":"3","key":"46_CR22","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1109\/TAU.1968.1161990","volume":"16","author":"AV Oppenheim","year":"1968","unstructured":"Oppenheim, A.V., Schafer, R.W., Stockham, T.: Nonlinear filtering of multiplied and convolved signals. IEEE Trans. Audio Electroacoust. 16(3), 437\u2013466 (1968)","journal-title":"IEEE Trans. Audio Electroacoust."},{"key":"46_CR23","doi-asserted-by":"crossref","unstructured":"Patel, T.B., Patil, H.A.: Combining evidences from Mel cepstral, cochlear filter cepstral and instantaneous frequency features for detection of natural vs. spoofed speech. In: INTERSPEECH, pp. 2062\u20132066, Dresden, Germany (Sept 2015)","DOI":"10.21437\/Interspeech.2015-467"},{"key":"46_CR24","unstructured":"Quatieri, T.F.: Discrete-Time Speech Signal Processing: Principles and Practice. $$1^{st}$$ edition, Pearson Education India, New Delhi (2015)"},{"key":"46_CR25","unstructured":"Schafer, R.W.: Echo Removal by Discrete Generalized Linear Filtering. MIT Research Laboratory of Electronics, Cambridge (1969)"},{"key":"46_CR26","doi-asserted-by":"crossref","unstructured":"Shiota, S., Villavicencio, F., Yamagishi, J., Ono, N., Echizen, I., Matsui, T.: Voice liveness detection for speaker verification based on a tandem single\/double-channel pop noise detector. In: Odyssey, vol. 2016, pp. 259\u2013263, Bilbao, Spain, June 2016","DOI":"10.21437\/Odyssey.2016-37"},{"key":"46_CR27","doi-asserted-by":"crossref","unstructured":"Tapkir, P.A., Patil, A.T., Shah, N., Patil, H.A.: Novel spectral root cepstral features for replay spoof detection. In: APSIPA-ASC, pp. 1945\u20131950, Honolulu, Hawaii, USA, November 2018","DOI":"10.23919\/APSIPA.2018.8659746"},{"key":"46_CR28","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.: Constant Q cepstral coefficients: a spoofing countermeasure for automatic speaker verification. Comput. Speech Lang. 45, 516\u2013535 (2017)","journal-title":"Comput. Speech Lang."},{"key":"46_CR29","doi-asserted-by":"crossref","unstructured":"Todisco, M., et al.: ASVspoof 2019: future horizons in spoofed and fake audio detection. In: INTERSPEECH, pp. 1008\u20131012, Graz, Austria, September 2019","DOI":"10.21437\/Interspeech.2019-2249"},{"key":"46_CR30","doi-asserted-by":"crossref","unstructured":"Tom, F., Jain, M., Dey, P.: End-to-end audio replay attack detection using deep convolutional networks with attention. In: INTERSPEECH, pp. 681\u2013685, Hyderabad, India, September 2018","DOI":"10.21437\/Interspeech.2018-2279"},{"key":"46_CR31","unstructured":"Vaidya, T., Zhang, Y., Sherr, M., Shields, C.: Cocaine noodles: exploiting the gap between human and machine speech recognition. In: 9th USENIX Workshop on Offensive Technologies (WOOT-2015), Washington, DC, USA, August 2015"},{"key":"46_CR32","doi-asserted-by":"crossref","unstructured":"Wickramasinghe, B., Irtza, S., Ambikairajah, E., Epps, J.: Frequency domain linear prediction features for replay spoofing attack detection. In: INTERSPEECH, pp. 661\u2013665, Hyderabad, India, September 2018","DOI":"10.21437\/Interspeech.2018-1574"},{"issue":"11","key":"46_CR33","doi-asserted-by":"publisher","first-page":"2884","DOI":"10.1109\/TIFS.2018.2833032","volume":"13","author":"X Wu","year":"2018","unstructured":"Wu, X., He, R., Sun, Z., Tan, T.: A light CNN for deep face representation with noisy labels. IEEE Trans. Inf. Forensics Secur. 13(11), 2884\u20132896 (2018)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"46_CR34","doi-asserted-by":"crossref","unstructured":"Wu, Z., et al.: ASVspoof 2015: the first automatic speaker verification spoofing and countermeasures challenge. In: INTERSPEECH, pp. 2037\u20132041, Dresden, Germany, September 2015","DOI":"10.21437\/Interspeech.2015-462"},{"key":"46_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, G., Yan, C., Ji, X., Zhang, T., Zhang, T., Xu, W.: Dolphinattack: inaudible voice commands. In: Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, pp. 103\u2013117. ACM, Dallas, TX, USA, October 2017","DOI":"10.1145\/3133956.3134052"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-87802-3_46","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T23:52:26Z","timestamp":1632268346000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87802-3_46"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030878016","9783030878023"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87802-3_46","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"22 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"St Petersburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/specom.nw.ru\/2021\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"163","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"74","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"45% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.5","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5.5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held online due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}