Veštačka inteligencija u službi forenzike glasa i govora
Sažetak
Uvod. Veštačka inteligencija predstavlja vrhunac razvoja savremenih tehnologija. Programiran da pomaže ljudima u obavljanju operacija koje opterećuju ili čak i prevazilaze njihove mogućnosti, ovaj kompjuterski sistem pronalazi svoju primenu u različitim područjima profesionalnog i svakodnevnog funkcionisanja. Jednu od oblasti u kojima resursi koje pruža veštačka inteligencija mogu biti dragoceni predstavljaju i forenzičke nauke. Cilj. Cilj rada je da se pomoću sistematizacije dostupne literature predstave mogućnosti veštačke inteligencije u kontekstu forenzike glasa i govora, zatim ograničenja, kao i potencijalne opasnosti od njene primene u sudskim postupcima. Metode. Literatura korišćena u radu je obezbeđena pretragom dostupnih baza podataka putem udaljenog pristupa, nakon čega se pristupilo sintezi relevantnih nalaza. Rezultati. Veštačka inteligencija je visokosofisticirano tehnološko dostignuće koje ima potencijal da u budućnosti transformiše različite forenzičke discipline. Zbog činjenice da je jezik jedan od najkompleksnijih društvenih fenomena, ali i zbog posledica koje bi mogle proisteći na osnovu analize u čiji način sprovođenja veštaci nemaju uvid, ova tehnologija nije uvrštena u zvanične i prihvaćene metode veštačenja glasa. Zaključak. Veštačka inteligencija može doprineti forenzičkim ispitivanjima glasa i govora, ali s obzirom na to da nedovoljna transparentnosti ovih sistema nameće suštinska etička pitanja, njena primena za sada ostaje ograničena na operacije sadržane u pripremnom delu postupka veštačenja. Povećanje transparentnosti sistema zasnovanih na veštačkoj inteligenciji, uz podrazumevane konstantne napore ka poboljšanju otpornosti i preciznosti, doprineće rešavanju etičkih nedoumica i prihvatanju ove tehnologije kao legitimne u sudskim postupcima.
Reference
2. Al Ajmi, S., Hayat, K., Al Obaidi, A. M., Kumar, N., Najmuldeen, M., & Magnier, B. (2022). Digital audio forensics: Blind human voice mimicry detection. arXiv preprint arXiv:2209.12573. https://doi.org/10.48550/arXiv.2209.12573
3. Alam, S., & Altiparmak, Z. (2024). XAI-CF - Examining the role of explainable artificial intelligence in cyber forensics. arXiv. https://doi.org/10.48550/arXiv.2402.02452
4. Anirudh, V. K. (2019, October 17). What Is Deep Learning: Definition, Framework, and Neural Networks [Web log post]. Retrieved July 12, 2020, from https://www.toolbox.com/tech/artificial-intelligence/tech-101/what-is-deep-learning-definition-framework-and-neural-networks/
5. Arjamand, M., Saleem, A., Basit, A., Iftikhar, S., Sharif, M., Cholistani, M. S., Farhan, M., Shumail, S., Khan, B. A., Ali, Z., Shahid, B., & Hasnain, M. (2024). The role of artificial intelligence in forensic science: Transforming investigations through technology. International Journal of Multidisciplinary Research and Publications (IJMRAP), 7(5), 67–70. https://ijmrap.com/wp-content/uploads/2024/10/IJMRAP-V7N5P52Y24.pdf
6. Ben Amor, I. (2024). Deep modeling based on voice attributes for explainable speaker recognition: Application in the forensic domain [Doctoral dissertation, Université d’Avignon]. HAL Archives. https://hal.science/tel-04634215
7. Bitter, C., Elizondo, D. A., & Watson, T. (2010). Application of artificial neural networks and related techniques to intrusion detection. IEEE World Congress on Computational Intelligence (WCCI 2010), 949–954. https://doi.org/10.1109/IJCNN.2010.5596532
8. Bonastre, J. F., Campbell, J. P., & Mason, J. S. D. (2010). Forensic speaker recognition. IEEE Signal Processing Magazine, 27(2), 95–103. https://doi.org/10.1109/MSP.2010.936730
9. de Lima, T. A., & Da-Costa Abreu, M. C. (2022). Phoneme analysis for multiple languages with fuzzy-based speaker identification. IET Biometrics, 11(6), 614–624. https://doi.org/10.1049/bme2.12078
10. Dilek, S., Çakır, H., & Aydın, M. (2015). Applications of artificial intelligence techniques to combating cyber crimes: A review. International Journal of Artificial Intelligence & Applications (IJAIA), 6(1), 21–39. https://doi.org/10.5121/ijaia.2015.6102
11. Dunsin, D., Ghanem, M. C., & Ouazzane, K. (2022). The use of artificial intelligence in digital forensics and incident response in a constrained environment. International Journal of Information and Communication Engineering, 16(8), 280–28
12. Durán, J. M., van der Vloed, D., Ruifrok, A., & Ypma, R. J. F. (2024). From understanding to justifying: Computational reliabilism for AI-based forensic evidence evaluation. Forensic Science International: Synergy, 9, 100554. https://doi.org/10.1016/j.fsisyn.2024.100554
13. Endah, S. N., Adhy, S., & Sutikno, S. (2017). Comparison of feature extraction MFCC and LPC in automatic speech recognition for Indonesian. TELKOMNIKA (Telecommunication Computing Electronics and Control), 15(1), 292–298. https://doi.org/10.12928/telkomnika.v15i1.3605
14. Franke, K. (2023). Artificial intelligence (AI) in forensic sciences. Wiley-Blackwell.
15. Franke, K., & Srihari, S. N. (2007, August). Computational forensics: Towards hybrid-intelligent crime investigation. In Third International Symposium on Information Assurance and Security (pp. 383-386). IEEE.
16. Hall, S. W., Sakzad, A., & Choo, K. R. (2021). Explainable artificial intelligence for digital forensics. WIREs Forensic Science, 4(2), 1–11. https://doi.org/10.1002/wfs2.1434
17. Hoelz, B., Ralha, C., & Geeverghese, R. (2009). Artificial intelligence applied to computer forensics. U Proceedings of the 2009 ACM Symposium on Applied Computing - SAC '09 (pp. 1181–1185). https://doi.org/10.1145/1529282.1529549
18. Ivanović, M., & Šešum, M. (2009). Jedan tip regionalne redukcije neakcentovanih slogova kao forenzički marker. U Zbornik radova 53. konferencije ETRAN (str. 1–4). Vrnjačka Banja, Srbija: Društvo za ETRAN.
19. Jadhav, E. B., Sankhla, M. S., & Kumar, R. (2020). Artificial intelligence: Advancing automation in forensic science & criminal investigation. Journal of Seybold Report, 15(8), 2064–2075. https://doi.org/10.2174/2666484401666220819111603
20. Jain, A. K., & Kumar, A. (2010). Biometrics of next generation: An overview. Second Generation Biometrics, 12(1), 2–3.
21. Jain, P., Chinmayee, P., Kaur, K., Chaudhary, S., Kaur, K., & Karunya, S. (2024a). Advancements in forensic voice analysis: Legal frameworks and technology integration. Asian Journal of Advances in Research, 7(1), 369–384. https://jasianresearch.com/index.php/AJOAIR/article/view/464
22. Jain, P., Ujjainia, P., Srivastava, A., Shrivastav, K., Rani, I., Vashisht, A., Behera, R., Moza, B., & Mukherjee, D. (2024b). Forensic perspective on voice biometrics and AI: A review. International Journal of Scientific Research in Science and Technology, 11(5), 49–63. https://doi.org/10.32628/IJSRST2411581
23. Jansen, F., Sánchez-Monedero, J., & Dencik, L. (2021). Biometric identity systems in law enforcement and the politics of (voice) recognition: The case of SiiP. Big Data & Society, 8(2), 49–63. https://doi.org/10.1177/20539517211063604
24. Kamble, Y., & Devarmani, N. G. (2024). Application of artificial intelligence (AI) in forensic investigation. In R. Mia, V. Panchal, S. Singla, & M. Jain (Eds.), Advanced and emerging development in multidisciplinary approaches in forensic science, digital forensic, law and criminology (pp. 197–204). AkiNik Publications. https://doi.org/10.22271/ed.book.2825
25. Kassem, M. A., & Lodhi, K. (2024). Revolutionizing forensic science: The role of artificial intelligence and machine learning. International Journal of Data Science, vi, 10–18. https://doi.org/10.5147/ijds.vi.255
26. Kovačević, J., & Šešum, M. (2012). Uticaj mehaničke modifikacije govora na akustičku strukturu govornih segmenata. U Zbornik radova 56. konferencije ETRAN (str. 1–4). Zlatibor, Srbija: Društvo za ETRAN.
27. Mitchell, F. (2014). The use of artificial intelligence in digital forensics: An introduction. Digital Evidence and Electronic Signature Law Review, 7. https://doi.org/10.14296/deeslr.v7i0.1922
28. Morrison, G. S., Enzinger, E., Ramos, D., González-Rodríguez, J., & Lozano-Díez, A. (2020). Statistical models in forensic voice comparison. In D. L. Banks, K. Kafadar, D. H. Kaye, & M. Tackett (Eds.), Handbook of forensic statistics (Ch. 20, pp. 451–497). CRC Press.
29. Negrão, M., & Domingues, P. (2021). SpeechToText: An open-source software for automatic detection and transcription of voice recordings in digital forensics. Forensic Science International: Digital Investigation, 38, 301223. https://doi.org/10.1016/j.fsidi.2021.301223
30. O'Hear, M. M. (2019). Appellate review of sentence explanations: Learning from the Wisconsin and federal experiences. Marquette Law Review, 103(2), 641–678. https://scholarship.law.marquette.edu/mulr/vol93/iss2/15/?utm_source=chatgpt.com
31. Patil, H. A., & Parhi, K. K. (2009). Variable length Teager energy based Mel cepstral features for identification of twins. In S. Chaudhury, A. N. Rajagopalan, D. S. Chauhan, S. Murty, & P. K. Biswas (Eds.), Pattern Recognition and Machine Intelligence (pp. 525–530). Springer. https://doi.org/10.1007/978-3-642-11164-8_85
32. Phonexia launches voice biometrics product for forensic investigations. (2024, January 1). Biometric Update. https://www.biometricupdate.com/202401/phonexia-launches-voice-biometrics-product-for-forensic-investigations
33. Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). "Why should I trust you?": Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1135–1144). ACM. https://doi.org/10.1145/2939672.2939778
34. Sal, F. (2019). Biometric techniques for personal identification & voice authentication. ResearchGate. https://doi.org/10.13140/RG.2.2.16351.61607
35. Singh, N., Agrawal, A., & Khan, R. A. (2018). Voice biometric: A technology for voice-based authentication. Advanced Science, Engineering and Medicine, 10(7–8), 754–759. https://doi.org/10.1166/asem.2018.2219
36. Singh, S. (2019). The role of speech technology in biometrics, forensics and man-machine interface. International Journal of Electrical and Computer Engineering, 9(1), 281–288. https://doi.org/10.11591/ijece.v9i1.pp281-288
37. Slovak, B. L., & Shepherd, S. M. (2020). Machine learning and forensic risk assessment: New frontiers. The Journal of Forensic Psychiatry & Psychology, 31(4), 571–581. https://doi.org/10.1080/14789949.2020.1779783
38. Susanto, S., & Nanda, D. S. (2024). Predicting the classification of high vowel sound by using artificial neural network: A study in forensic linguistics. IAES International Journal of Artificial Intelligence (IJ-AI), 13(1), 195–200. https://doi.org/10.11591/ijai.v13.i1.pp195-200
39. Šešum, M. (2013). Komparativna analiza formantnih struktura glasova sestara i glasova monozigotnih bliznakinja. Beogradska defektološka škola, 19(3), 515–527.
40. Šešum, M. (2021). Forenzička fonetika-identifikacija govornika. U: Knežević, S. (ur.), Forenzičko računovodstvo, istražne radnje, ljudski faktor i primenjeni alati (str. 828- 859). Beograd: Fakultet organizacionih nauka.. ISBN: 978-86-7680-393-4
41. Šešum, M. (2022). Uloga surdologa i logopeda u forenzičkoj analizi glasa i govora. V simpozijum logopeda Srbije: U Timski rad u logopediji i defektologijii (str. 280-290). Udruženje logopeda Srbije.
42. Šešum, M. (2024). Forenzički značaj maskiranja glasa i govora. U Zbornik sažetaka radova IX simpozijuma logopeda Srbije: Transdisciplinarnost u logopediji danas (str. 11). Udruženje logopeda Srbije. ISBN 978-86-904732-2-9.
43. Šešum, M., Kovačević, J. (2015). Forenzička fonetika. Vodič za primenu Zakonika o krivičnom postupku Republike Srbije (str. 90–105). Grafol
44. Šešum, M., & Petrović, E. (2024). The complexity of speaker identification based on voice and speech and its application in forensics. In S. H. Fazeli (Ed.), The Ninth International Conference on Languages, Linguistics, Translation and Literature – Full Articles (Volume One) (pp. 90-108), Ahwaz Publication of Research and Sciences. ISBN 978-622-90390-9-0
45. Tistarelli, M., Grosso, E., & Meuwly, D. (2014). Biometrics in forensic science: Challenges, lessons and new technologies. U Proceedings of the International Workshop on Biometric Authentication (pp. 153–164). Springer. https://doi.org/10.1007/978-3-319-05050-8_15
46. Watanabe, S., Delcroix, M., Metze, F., & Hershey, J. R. (Eds.). (2017). New era for robust speech recognition. Springer International Publishing. https://doi.org/10.1007/978-3-319-64680-0
Sva prava zadržana (c) 2025 Specijalna edukacija i rehabilitacija

Ovaj rad je pod Creative Commons Autorstvo-Deli pod istim uslovima 4.0 međunarodnom licencom.
