{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T22:59:27Z","timestamp":1752101967591,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":17,"publisher":"Springer Singapore","isbn-type":[{"type":"print","value":"9789811905223"},{"type":"electronic","value":"9789811905230"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-981-19-0523-0_17","type":"book-chapter","created":{"date-parts":[[2022,2,28]],"date-time":"2022-02-28T06:02:45Z","timestamp":1646028165000},"page":"257-265","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Identification of\u00a0Synthetic Spoofed Speech with\u00a0Deep Capsule Network"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3853-5380","authenticated-orcid":false,"given":"Terui","family":"Mao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5241-7276","authenticated-orcid":false,"given":"Diqun","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3216-2998","authenticated-orcid":false,"given":"Yongkang","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2576-8705","authenticated-orcid":false,"given":"Randing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,3,1]]},"reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Toda, T., et al.: The voice conversion challenge. In: Interspeech, 1632\u20131636 (2016)","DOI":"10.21437\/Interspeech.2016-1066"},{"key":"17_CR2","unstructured":"Huang, W.C., Lo, C.C., Hwang, H.T., Tsao, Y., Wang, H.M.: Wavenet vocoder and its applications in voice conversion. In: The 30th ROCLING Conference on Computational Linguistics and Speech Processing (ROCLING) (2018)"},{"key":"17_CR3","unstructured":"Oord, A.V.D., et al.: A generative model for raw audio. arXiv preprint arXiv:1609.03499 (2016)"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Wu, Z., Watts, O., King, S.: Merlin: an open source neural network speech synthesis system. In: 9th ISCA Speech Synthesis Workshop, pp. 202\u2013207 (2016)","DOI":"10.21437\/SSW.2016-33"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Juvela, L., et al.: Speech waveform synthesis from MFCC sequences with generative adversarial networks. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5679\u20135683 (2018)","DOI":"10.1109\/ICASSP.2018.8461852"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Kinnunen, T., et al.: t-DCF: a detection cost function for the tandem assessment of spoofing countermeasures and automatic speaker verification. arXiv preprint arXiv:1804.09618 (2018)","DOI":"10.21437\/Odyssey.2018-44"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Sahidullah, M., Kinnunen, T., Hanilci, C.: A comparison of features for synthetic speech detection. In: The International Speech Communication Association (ISCA) (2015)","DOI":"10.21437\/Interspeech.2015-472"},{"key":"17_CR8","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: Sixteenth Annual Conference of the International Speech Communication Association (2015)","DOI":"10.21437\/Interspeech.2015-467"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Todisco, M., Delgado, H., Evans, N: A new feature for automatic speaker verification anti-spoofing: constant Q cepstral coefficients. Odyssey: The Speaker and Language Recognition Workshop, pp. 283\u2013290 (2016)","DOI":"10.21437\/Odyssey.2016-41"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Alzantot, M., Wang, Z., Srivastava, M.S.: Deep residual neural networks for audio spoofing detection: deep residual neural networks for audio spoofing detection. In: Interspeech, pp. 1078\u20131082 (2019)","DOI":"10.21437\/Interspeech.2019-3174"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Lai, C.I., Chen, N., Villalba, J., et al.: ASSERT: anti-spoofing with squeeze-excitation and residual networks: deep residual neural networks for audio spoofing detection. In: Interspeech, pp. 1013\u20131017 (2019)","DOI":"10.21437\/Interspeech.2019-1794"},{"key":"17_CR12","unstructured":"Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules: advances. In: Neural Information Processing Systems, pp. 3856\u20133886 (2017)"},{"key":"17_CR13","unstructured":"Tiwari, V.: MFCC and its applications in speaker recognition: Int. J. Emerg. Technol. 1, 19\u201322 (2010)"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Todisco, M., Delgado, H., Evans, N.: Constant Q cepstral coefficients: a spoofing counter-measure for automatic speaker verification. Comput. Speech Lang. 45, 516\u2013535 (2017)","DOI":"10.1016\/j.csl.2017.01.001"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Reynolds, D.A., Rose, R.C.: Robust text-independent speaker identification using Gaussian mixture speaker models: IEEE Trans. Speech Audio Process. 3, 72\u201383 (1995)","DOI":"10.1109\/89.365379"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Reynolds, D.A., Quatieri, T.F., Dunn, R.S.: Speaker verification using adapted Gaussian mixture models. Digit. Sig. Process. 10, 19\u201341 (2000)","DOI":"10.1006\/dspr.1999.0361"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Jaiswal, A., AbdAlmageed, W., Wu, Y., Natarajan, P.: CapsuleGAN: generative adversarial capsule network. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-11015-4_38"}],"container-title":["Communications in Computer and Information Science","Frontiers in Cyber Security"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-19-0523-0_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,28]],"date-time":"2022-02-28T06:05:07Z","timestamp":1646028307000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-19-0523-0_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9789811905223","9789811905230"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-981-19-0523-0_17","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"1 March 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"FCS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Frontiers in Cyber Security","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Haikou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"17 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"fcs2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.icfcs.com.cn\/fcs2021","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-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":"58","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":"20","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":"2","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":"34% - 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":"2.7","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":"4.3","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)"}}]}}