{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T17:44:51Z","timestamp":1765993491121,"version":"3.40.3"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031780134"},{"type":"electronic","value":"9783031780141"}],"license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-78014-1_13","type":"book-chapter","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T12:25:38Z","timestamp":1732191938000},"page":"171-184","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Voice Cloning and\u00a0Mismatch Conditions in\u00a0Forensic Automatic Speaker Recognition"],"prefix":"10.1007","author":[{"given":"Jacek","family":"Kudera","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miriam","family":"Coccia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sharifeh","family":"Fadaeijouybari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Till","family":"Preidt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akshay","family":"Ranjan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Angelika","family":"Braun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"13_CR1","unstructured":"Phonexia Voice Inspector Version 4.0.3. https:\/\/www.phonexia.com\/use-case\/audio-forensics-software\/"},{"key":"13_CR2","unstructured":"Phonexia Voice Inspector - User Manual. Phonexia s.r.o"},{"key":"13_CR3","unstructured":"PlayHT. https:\/\/github.com\/playht"},{"key":"13_CR4","doi-asserted-by":"publisher","first-page":"517","DOI":"10.2165\/00007256-200333070-00004","volume":"33","author":"J Achten","year":"2003","unstructured":"Achten, J., Jeukendrup, A.E.: Heart rate monitoring: applications and limitations. Sports Med. 33, 517\u2013538 (2003)","journal-title":"Sports Med."},{"key":"13_CR5","unstructured":"Braun, A., Kudera, J.: Testing phonexia under real-world conditions. In: Conference talk at 32nd IAFPA Conference, L\u2019Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al and the Royal Canadian Mounted Police, 28\u201331 July 2024 (2024)"},{"issue":"2\u20133","key":"13_CR6","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1016\/j.csl.2005.08.001","volume":"20","author":"N Br\u00fcmmer","year":"2006","unstructured":"Br\u00fcmmer, N., Du Preez, J.: Application-independent evaluation of speaker detection. Comput. Speech Lang. 20(2\u20133), 230\u2013275 (2006)","journal-title":"Comput. Speech Lang."},{"key":"13_CR7","doi-asserted-by":"publisher","unstructured":"Br\u00fcmmer, N., Swart, A.: Bayesian calibration for forensic evidence reporting. In: Proceedings of the Interspeech 2014, pp. 388\u2013392 (2014). https:\/\/doi.org\/10.21437\/Interspeech.2014-90","DOI":"10.21437\/Interspeech.2014-90"},{"issue":"2\u20133","key":"13_CR8","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/S0167-6393(99)00078-3","volume":"31","author":"C Champod","year":"2000","unstructured":"Champod, C., Meuwly, D.: The inference of identity in forensic speaker recognition. Speech Commun. 31(2\u20133), 193\u2013203 (2000)","journal-title":"Speech Commun."},{"key":"13_CR9","unstructured":"Drygajlo, A., Jessen, M., Gfroerer, S., Wagner, I., Vermeulen, J., Niemi, T.: Methodological guidelines for best practice in forensic semiautomatic and automatic speaker recognition. Verlag f\u00fcr Polizeiwissenschaft Frankfurt (2015)"},{"key":"13_CR10","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.specom.2015.03.001","volume":"70","author":"E Enzinger","year":"2015","unstructured":"Enzinger, E., Morrison, G.S.: Mismatched distances from speakers to telephone in a forensic-voice-comparison case. Speech Commun. 70, 28\u201341 (2015)","journal-title":"Speech Commun."},{"key":"13_CR11","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1515\/9780748635788-012","volume":"8","author":"A Eriksson","year":"2010","unstructured":"Eriksson, A., Llamas, C., Watt, D.: The disguised voice: imitating accents or speech styles and impersonating individuals. Lang. Identities 8, 86\u201396 (2010)","journal-title":"Lang. Identities"},{"issue":"38","key":"13_CR12","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1016\/S1355-0306(98)72105-7","volume":"3","author":"IW Evett","year":"1998","unstructured":"Evett, I.W.: Towards a uniform framework for reporting opinions in forensic science casework. Sci. Justice 3(38), 198\u2013202 (1998)","journal-title":"Sci. Justice"},{"key":"13_CR13","unstructured":"Fecher, N.: Effects of forensically-relevant facial concealment on acoustic and perceptual properties of consonants. Ph.D. thesis, University of York (2014). https:\/\/etheses.whiterose.ac.uk\/7397\/"},{"key":"13_CR14","unstructured":"Fecher, N., Watt, D.: Speaking Under Cover: The Effect of Face-concealing Garments on Spectral Properties of Fricatives, pp. 663\u2013666 (2011)"},{"issue":"3","key":"13_CR15","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1016\/j.jvoice.2021.01.026","volume":"37","author":"ML Fiorella","year":"2023","unstructured":"Fiorella, M.L., Cavallaro, G., Di Nicola, V., Quaranta, N.: Voice differences when wearing and not wearing a surgical mask. J. Voice 37(3), 467-e1 (2023)","journal-title":"J. Voice"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Gama, R., Castro, M.E., van Lith-Bijl, J.T., Desuter, G.: Does the wearing of masks change voice and speech parameters? In: European Archives of Oto-Rhino-Laryngology, pp.\u00a01\u20138 (2021)","DOI":"10.1007\/s00405-021-07086-9"},{"key":"13_CR17","unstructured":"Hughes, V.: The definition of the relevant population and the collection of data for likelihood ratio-based forensic voice comparison. Ph.D. thesis, University of York (2014)"},{"key":"13_CR18","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1016\/j.specom.2014.10.006","volume":"66","author":"V Hughes","year":"2015","unstructured":"Hughes, V., Foulkes, P.: The relevant population in forensic voice comparison: effects of varying delimitations of social class and age. Speech Commun. 66, 218\u2013230 (2015)","journal-title":"Speech Commun."},{"key":"13_CR19","unstructured":"Hughes, V., Harrison, P., Foulkes, P., French, P., Gully, A.J.: Effects of formant analysis settings and channel mismatch on semi-automatic forensic voice comparison. In: Proceedings of the International Congress of Phonetic Sciences, 4\u201310 August 2019, Melbourne, pp. 3080\u20133084 (2019)"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Hughes, V., Llamas, C., Kettig, T.: Eliciting and evaluating likelihood ratios for speaker recognition by human listeners under forensically realistic channel-mismatched conditions. In: Proceedings of INTERSPEECH 2022, pp. 5238\u20135242 (2022)","DOI":"10.21437\/Interspeech.2022-490"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Hutiri, W., Papakyriakopoulos, O., Xiang, A.: Not my voice! a taxonomy of ethical and safety harms of speech generators. arXiv preprint arXiv:2402.01708 (2024)","DOI":"10.1145\/3630106.3658911"},{"key":"13_CR22","unstructured":"Joseph, J., Lazzarotti, M.A.: As voice recognition technology market surges, organizations face privacy and cybersecurity concerns. Article. The National Law Review (2020)"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Juvela, L., Wang, X.: Collaborative watermarking for adversarial speech synthesis. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 11231\u201311235. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10448134"},{"key":"13_CR24","doi-asserted-by":"publisher","unstructured":"Kheria, I., Karani, R.: CloneAI: a deep learning-based approach for\u00a0cloned voice detection. In: Nanda, S.J., Yadav, R.P., Gandomi, A.H., Saraswat, M. (eds.) ICDSA 2023, vol. 3, pp. 267\u2013282. Springer, Singapore (2024). https:\/\/doi.org\/10.1007\/978-981-99-7817-5_21","DOI":"10.1007\/978-981-99-7817-5_21"},{"key":"13_CR25","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/j.specom.2015.10.002","volume":"75","author":"A Leemann","year":"2015","unstructured":"Leemann, A., Kolly, M.J.: Speaker-invariant suprasegmental temporal features in normal and disguised speech. Speech Commun. 75, 97\u2013122 (2015)","journal-title":"Speech Commun."},{"key":"13_CR26","doi-asserted-by":"publisher","unstructured":"Liu, X., Sahidullah, M., Lee, K.A., Kinnunen, T.: Speaker-aware anti-spoofing. In: Proceedings of the INTERSPEECH 2023, pp. 2498\u20132502 (2023). https:\/\/doi.org\/10.21437\/Interspeech.2023-1323","DOI":"10.21437\/Interspeech.2023-1323"},{"issue":"9","key":"13_CR27","first-page":"80","volume":"2","author":"C Llamas","year":"2008","unstructured":"Llamas, C., Harrison, P., Donnelly, D., Watt, D.: Effects of different types of face coverings on speech acoustics and intelligibility. York Papers Linguist. Ser. 2(9), 80\u2013104 (2008)","journal-title":"York Papers Linguist. Ser."},{"issue":"9","key":"13_CR28","first-page":"80","volume":"2","author":"C Llamas","year":"2008","unstructured":"Llamas, C., Harrison, P., Donnelly, D., Watt, D.: Effects of different types of face coverings on speech acoustics and intelligibility. York Papers Linguist. Ser. 2(9), 80\u2013104 (2008)","journal-title":"York Papers Linguist. Ser."},{"issue":"1","key":"13_CR29","first-page":"27","volume":"7","author":"KD Manley","year":"2022","unstructured":"Manley, K.D., Chan, J.C., Wells, G.L.: Improving face identification of mask-wearing individuals. Cognit. Res.: Princip. Implicat. 7(1), 27 (2022)","journal-title":"Cognit. Res.: Princip. Implicat."},{"issue":"1","key":"13_CR30","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1558\/ijsll.v3i1.160","volume":"3","author":"H Masthoff","year":"2013","unstructured":"Masthoff, H.: A report on a voice disguise experiment. Int. J. Speech Lang. Law 3(1), 160\u2013167 (2013)","journal-title":"Int. J. Speech Lang. Law"},{"key":"13_CR31","unstructured":"McKenna, L., et\u00a0al.: ENFSI Guideline for Evaluative Reporting in Forensic Science: Strengthening the Evaluation of Forensic Results Across Europe (STEOFRAE), pp. 30\u201341. European Network of Forensic Science Institutes, Wiesbaden (2015). http:\/\/enfsi.eu\/wp-content\/uploads\/2016\/09\/m1_guideline.pdf"},{"issue":"10","key":"13_CR32","doi-asserted-by":"publisher","first-page":"750","DOI":"10.1136\/bjsm.2008.046342","volume":"43","author":"CR Mikus","year":"2009","unstructured":"Mikus, C.R., Earnest, C.P., Blair, S.N., Church, T.S.: Heart rate and exercise intensity during training: observations from the drew study. Br. J. Sports Med. 43(10), 750\u2013755 (2009)","journal-title":"Br. J. Sports Med."},{"issue":"21","key":"13_CR33","doi-asserted-by":"publisher","first-page":"4458","DOI":"10.3390\/electronics12214458","volume":"12","author":"K Milewski","year":"2023","unstructured":"Milewski, K., Zaporowski, S., Czy\u017cewski, A.: Comparison of the ability of neural network model and humans to detect a cloned voice. Electronics 12(21), 4458 (2023)","journal-title":"Electronics"},{"key":"13_CR34","doi-asserted-by":"crossref","unstructured":"Morrison, G.S., et\u00a0al.: Consensus on validation of forensic voice comparison. Sci. Justice 61(3), 299\u2013309 (2021). https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1355030621000083","DOI":"10.1016\/j.scijus.2021.02.002"},{"issue":"1\u20133","key":"13_CR35","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.forsciint.2010.11.001","volume":"208","author":"GS Morrison","year":"2011","unstructured":"Morrison, G.S., Zhang, C., Rose, P.: An empirical estimate of the precision of likelihood ratios from a forensic-voice-comparison system. Forensic Sci. Int. 208(1\u20133), 59\u201365 (2011)","journal-title":"Forensic Sci. Int."},{"key":"13_CR36","unstructured":"Rhodes, R.W.: Assessing the strength of non-contemporaneous forensic speech evidence. Ph.D. thesis, University of York (2012)"},{"key":"13_CR37","unstructured":"Ruggiero, G., Zovato, E., Di\u00a0Caro, L., Pollet, V.: Voice cloning: a multi-speaker text-to-speech synthesis approach based on transfer learning. arXiv preprint arXiv:2102.05630 (2021)"},{"key":"13_CR38","unstructured":"San\u00a0Roman, R., Fernandez, P., Elsahar, H., D\u00e9fossez, A., Furon, T., Tran, T.: Proactive detection of voice cloning with localized watermarking. In: International Conference on Machine Learning, vol.\u00a0235 (2024)"},{"key":"13_CR39","doi-asserted-by":"publisher","unstructured":"Jin Shim, H., Gonzalez Hautam\u00e4ki, R., Sahidullah, M., Kinnunen, T.: How to construct perfect and worse-than-coin-flip spoofing countermeasures: a word of warning on shortcut learning. In: Proceedings of the INTERSPEECH 2023, pp. 785\u2013789 (2023). https:\/\/doi.org\/10.21437\/Interspeech.2023-1901","DOI":"10.21437\/Interspeech.2023-1901"},{"key":"13_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2020.102809","volume":"106","author":"M Taskiran","year":"2020","unstructured":"Taskiran, M., Kahraman, N., Erdem, C.E.: Face recognition: past, present and future (a review). Digit. Signal Process. 106, 102809 (2020)","journal-title":"Digit. Signal Process."},{"issue":"1","key":"13_CR41","first-page":"91","volume":"7","author":"HK Wong","year":"2022","unstructured":"Wong, H.K., Estudillo, A.J.: Face masks affect emotion categorisation, age estimation, recognition, and gender classification from faces. Cognit. Res.: Princip. Implicat. 7(1), 91 (2022)","journal-title":"Cognit. Res.: Princip. Implicat."}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78014-1_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T15:06:38Z","timestamp":1736348798000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78014-1_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"ISBN":["9783031780134","9783031780141"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78014-1_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"22 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors declare no conflict of interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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":"Belgrade","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Serbia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/specom2024.ftn.uns.ac.rs\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}