{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T11:58:45Z","timestamp":1774267125477,"version":"3.50.1"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031483080","type":"print"},{"value":"9783031483097","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-48309-7_12","type":"book-chapter","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:03:21Z","timestamp":1700597001000},"page":"142-155","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Source and\u00a0System-Based Modulation Approach for\u00a0Fake Speech Detection"],"prefix":"10.1007","author":[{"given":"Rishith","family":"Sadashiv T. N.","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Devesh","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ayush","family":"Agarwal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Moakala","family":"Tzudir","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jagabandhu","family":"Mishra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S. R. Mahadeva","family":"Prasanna","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,22]]},"reference":[{"key":"12_CR1","unstructured":"Fraudsters Used AI to Mimic CEO\u2019s Voice in Unusual Cybercrime Case. https:\/\/www.wsj.com\/articles\/fraudsters-use-ai-to-mimic-ceos-voice-in-unusual-cybercrime-case-11567157402"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Alzantot, M., Wang, Z., Srivastava, M.B.: Deep residual neural networks for audio spoofing detection. arXiv preprint arXiv:1907.00501 (2019)","DOI":"10.21437\/Interspeech.2019-3174"},{"key":"12_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115465","volume":"184","author":"DM Ballesteros","year":"2021","unstructured":"Ballesteros, D.M., Rodriguez-Ortega, Y., Renza, D., Arce, G.: Deep4snet: deep learning for fake speech classification. Expert Syst. Appl. 184, 115465 (2021)","journal-title":"Expert Syst. Appl."},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Black, A.W.: CMU wilderness multilingual speech dataset. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5971\u20135975. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683536"},{"key":"12_CR5","doi-asserted-by":"publisher","unstructured":"Cassani, R., Albuquerque, I., Monteiro, J., Falk, T.H.: AMA: an open-source amplitude modulation analysis toolkit for signal processing applications. In: 2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP), pp. 1\u20134 (2019). https:\/\/doi.org\/10.1109\/GlobalSIP45357.2019.8969210","DOI":"10.1109\/GlobalSIP45357.2019.8969210"},{"issue":"5","key":"12_CR6","doi-asserted-by":"publisher","first-page":"1024","DOI":"10.1109\/JSTSP.2020.2999185","volume":"14","author":"A Chintha","year":"2020","unstructured":"Chintha, A., et al.: Recurrent convolutional structures for audio spoof and video deepfake detection. IEEE J. Selected Topics Signal Process. 14(5), 1024\u20131037 (2020)","journal-title":"IEEE J. Selected Topics Signal Process."},{"issue":"1","key":"12_CR7","first-page":"227","volume":"43","author":"X Fang","year":"2023","unstructured":"Fang, X., et al.: Semi-supervised end-to-end fake speech detection method based on time-domain waveforms. J. Comput. Appl. 43(1), 227 (2023)","journal-title":"J. Comput. Appl."},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Hore, A., Ziou, D.: Image quality metrics: PSNR vs. SSIM. In: 2010 20th International Conference on Pattern Recognition, pp. 2366\u20132369. IEEE (2010)","DOI":"10.1109\/ICPR.2010.579"},{"key":"12_CR10","unstructured":"Ito, K., Johnson, L.: The LJ speech dataset. https:\/\/keithito.com\/LJ-Speech-Dataset\/ (2017)"},{"issue":"3","key":"12_CR11","doi-asserted-by":"publisher","first-page":"3447","DOI":"10.1007\/s13369-021-06297-w","volume":"47","author":"J Khochare","year":"2021","unstructured":"Khochare, J., Joshi, C., Yenarkar, B., Suratkar, S., Kazi, F.: A deep learning framework for audio deepfake detection. Arab. J. Sci. Eng. 47(3), 3447\u20133458 (2021). https:\/\/doi.org\/10.1007\/s13369-021-06297-w","journal-title":"Arab. J. Sci. Eng."},{"key":"12_CR12","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1007\/978-3-031-20980-2_35","volume-title":"Speech and Computer: 24th International Conference, SPECOM 2022, Gurugram, India, November 14\u201316, 2022, Proceedings","author":"D Kumar","year":"2022","unstructured":"Kumar, D., Patil, P.K.V., Agarwal, A., Prasanna, S.R.M.: Fake speech detection using OpenSMILE features. In: Prasanna, S.R.M., Karpov, A., Samudravijaya, K., Agrawal, S.S. (eds.) Speech and Computer: 24th International Conference, SPECOM 2022, Gurugram, India, November 14\u201316, 2022, Proceedings, pp. 404\u2013415. Springer International Publishing, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20980-2_35"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Lei, Z., Yang, Y., Liu, C., Ye, J.: Siamese convolutional neural network using gaussian probability feature for spoofing speech detection. In: INTERSPEECH, pp. 1116\u20131120 (2020)","DOI":"10.21437\/Interspeech.2020-2723"},{"key":"12_CR14","doi-asserted-by":"publisher","unstructured":"Magazine, R., Agarwal, A., Hedge, A., Prasanna, S.M.: Fake speech detection using modulation spectrogram. In: Speech and Computer: 24th International Conference, SPECOM 2022, Gurugram, India, November 14\u201316, 2022, Proceedings. pp. 451\u2013463. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20980-2_39","DOI":"10.1007\/978-3-031-20980-2_39"},{"issue":"4","key":"12_CR15","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":"12_CR16","doi-asserted-by":"crossref","unstructured":"Mishra, J., Pati, D., Prasanna, S.M.: Modelling glottal flow derivative signal for detection of replay speech samples. In: 2019 National Conference on Communications (NCC), pp. 1\u20135. IEEE (2019)","DOI":"10.1109\/NCC.2019.8732249"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Mishra, J., Singh, M., Pati, D.: LP residual features to counter replay attacks. In: 2018 International Conference on Signals and Systems (ICSigSys), pp. 261\u2013266. IEEE (2018)","DOI":"10.1109\/ICSIGSYS.2018.8372769"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Mishra, J., Singh, M., Pati, D.: Processing linear prediction residual signal to counter replay attacks. In: 2018 International Conference on Signal Processing and Communications (SPCOM), pp. 95\u201399. IEEE (2018)","DOI":"10.1109\/SPCOM.2018.8724390"},{"issue":"19","key":"12_CR19","doi-asserted-by":"publisher","first-page":"4050","DOI":"10.3390\/app9194050","volume":"9","author":"Y Ning","year":"2019","unstructured":"Ning, Y., He, S., Wu, Z., Xing, C., Zhang, L.J.: A review of deep learning based speech synthesis. Appl. Sci. 9(19), 4050 (2019)","journal-title":"Appl. Sci."},{"issue":"10","key":"12_CR20","doi-asserted-by":"publisher","first-page":"1243","DOI":"10.1016\/j.specom.2006.06.002","volume":"48","author":"SM Prasanna","year":"2006","unstructured":"Prasanna, S.M., Gupta, C.S., Yegnanarayana, B.: Extraction of speaker-specific excitation information from linear prediction residual of speech. Speech Commun. 48(10), 1243\u20131261 (2006)","journal-title":"Speech Commun."},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Reimao, R., Tzerpos, V.: For: a dataset for synthetic speech detection. In: 2019 International Conference on Speech Technology and Human-Computer Dialogue (SpeD), pp. 1\u201310. IEEE (2019)","DOI":"10.1109\/SPED.2019.8906599"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Siddhartha, S., Mishra, J., Prasanna, S.M.: Language specific information from LP residual signal using linear sub band filters. In: 2020 National Conference on Communications (NCC), pp. 1\u20135. IEEE (2020)","DOI":"10.1109\/NCC48643.2020.9056005"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Todisco, M., et al.: Asvspoof 2019: future horizons in spoofed and fake audio detection. arXiv preprint arXiv:1904.05441 (2019)","DOI":"10.21437\/Interspeech.2019-2249"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Wang, C., et al.: Fully automated end-to-end fake audio detection. In: Proceedings of the 1st International Workshop on Deepfake Detection for Audio Multimedia, pp. 27\u201333 (2022)","DOI":"10.1145\/3552466.3556530"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Wijethunga, R., Matheesha, D., Al Noman, A., De Silva, K., Tissera, M., Rupasinghe, L.: Deepfake audio detection: a deep learning based solution for group conversations. In: 2020 2nd International Conference on Advancements in Computing (ICAC). vol. 1, pp. 192\u2013197. IEEE (2020)","DOI":"10.1109\/ICAC51239.2020.9357161"},{"key":"12_CR26","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 (2015)","DOI":"10.21437\/Interspeech.2015-462"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Yamamoto, R., Song, E., Kim, J.M.: Parallel wavegan: a fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6199\u20136203. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Yi, J., et al.: Add 2022: the first audio deep synthesis detection challenge. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 9216\u20139220. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Zen, H., et al.: Libritts: a corpus derived from librispeech for text-to-speech. arXiv preprint arXiv:1904.02882 (2019)","DOI":"10.21437\/Interspeech.2019-2441"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-48309-7_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:10:49Z","timestamp":1700597449000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-48309-7_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031483080","9783031483097"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-48309-7_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"All views and data related to information technology, and anything deemed to be \u201ccyber security\u201d are made on behalf of the authors of this paper and not on behalf of McAfee.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclaimer"}},{"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":"Dharwad","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iitdh.ac.in\/specom-2023\/","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":"174","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":"94","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":"54% - 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","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","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)"}}]}}