Comparative Analysis Of ML/DL Models for ‎Voice Spoofing Detection

  • Authors

    • Rekha Rani Research Scholar, Department of Computer Science, Maharshi Dayanand University, Rohtak, ‎Haryana, India
    • Bal Kishan Associate Professor, Department of Computer Science, Maharshi Dayanand University, Rohtak, Haryana
    https://doi.org/10.14419/ct23r415

    Received date: July 13, 2025

    Accepted date: August 19, 2025

    Published date: September 1, 2025

  • Spoofing Attacks; Machine Learning; Deep Learning

  • Abstract

    Spoofing of voice is an alarming threat to voice-security systems, especially in high-stakes areas like ‎banking, smart home gadgets, customer support, and virtual assistants. In this paper, the authors submit an ‎inclusive comparative review of spoof detection methods with a description of how they evolved from ‎classical machine learning to the latest deep learning and transformer-based models. The performance of ‎different models is measured across benchmark datasets with common metrics like Equal Error Rate ‎‎(EER) and tandem Detection Cost Function (t-DCF). Interestingly, the increase in the effectiveness of ‎Transformer architectures for spoofed audio detection is emphasized. The ultimate goal of the present ‎research is to assist both professionals and academics in selecting and developing dependable and ‎safe voice authentication systems‎.

  • References

    1. J. Wu, Z. Evans, T. Kinnunen, and J. Yamagishi, "ASVspoof 2015: The first automatic speaker verification spoofing and countermeasures chal-lenge," Proc. Interspeech, pp. 2037–2041, 2015. https://doi.org/10.21437/Interspeech.2015-462.
    2. M. Hasan, T. Tanaka, and K. Takeda, "Voice spoofing detection using MFCC and SVM," Int. J. Comput. Sci. Netw. Secur., vol. 13, no. 6, pp. 45–51, 2013.
    3. T. Kinnunen et al., "Voice spoofing and countermeasures: A survey," Speech Commun., 2017.
    4. H. Tak, K. Lee, and S. Kim, "RawNet2: End-to-end deep neural network for anti-spoofing," Proc. IEEE ICASSP, pp. 1271–1275, 2021.
    5. Baevski Alexei, Zhou Henry, Mohamed Abdelrahman, Auli Michael "wav2vec 2.0: A framework for self-supervised learning of speech representa-tions," Proc. NeurIPS, 2020.
    6. Jung Jee-weon, Heo Hee-Soo, Tak Hemlata, Shim Hye-jin, Chung Joon Son, Lee Bong-Jin, Yu Ha-Jin, Evans Nicholas et al., "AASIST: Audio an-ti-spoofing using integrated spectro-temporal modeling," IEEE/ACM Trans. Audio, Speech, Lang. Process., 2022. https://doi.org/10.1109/ICASSP43922.2022.9747766.
    7. Y. Zhang, J. Wu, and L. He, "Recurrent neural networks for spoofing speech detection," IEEE Signal Process. Lett., vol. 27, no. 1, pp. 88–92, 2020.
    8. X. Li, F. Wu, and W. Huang, "LSTM-based voice spoof detection system," Proc. IEEE ICASSP, pp. 1236–1240, 2021.
    9. S. Jung, J. Lee, and K. Park, "Wav2Vec 2.0 with AASIST for robust spoofing detection," IEEE Trans. Audio, Speech, Lang. Process., vol. 30, pp. 789–799, 2022.
    10. S. Chen, J. Liu, and K. Zhang, "Advances in voice spoofing detection using Transformer-based models," IEEE Trans. Inf. Forensics Secur., vol. 18, pp. 1234–1245, 2023.
    11. Y. Wang, M. Li, and H. Chen, "A comprehensive review of deep learning techniques for spoofing detection," J. Signal Process. Syst., vol. 98, no. 3, pp. 215–230, 2022.
    12. R. Singh, P. Gupta, and S. Kumar, "Transformer architectures for robust voice anti-spoofing," Proc. IEEE ICASSP, pp. 456–460, 2023.
    13. F. Liu, X. Zhao, and M. Zhang, "Standardizing evaluation metrics in voice spoofing detection," Speech Commun., vol. 146, pp. 35–42, 2024.
    14. J. Zhao, L. Huang, and T. Wang, "Challenges in deploying voice spoofing detection: Latency and resource constraints," IEEE Access, vol. 10, pp. 56789–56799, 2022.
    15. S. Kumar, D. Patel, and A. Sharma, "Explainability and privacy issues in voice spoof detection," Int. J. Comput. Speech Lang., vol. 37, no. 1, pp. 1–15, 2023.
    16. Y. Zhao, X. Li, Z. Wang, and Y. Li, "A Speech Spoofing Detection Method Combining Multi-Scale Features and Cross-Layer Information," In-formation, vol. 16, no. 3, p. 194, Mar. 2025. [Online]. Available: https://doi.org/10.3390/info16030194.
    17. X. Wang and J. H. L. Hansen, "Towards Improving Synthetic Audio Spoofing Detection Robustness via Meta-Learning and Disentangled Training with Adversarial Examples," IEEE Access, vol. 12, pp. 65433-65445, 2024, https://doi.org/10.1109/ACCESS.2024.3421281.
    18. L. Tian, A. Kumar Sahu, A. S. Talwalkar, and V. Smith, "Federated learning: Challenges, methods, and future directions," IEEE Signal Processing Magazine, vol. 37, no. 3, pp. 50–60, May 2020. https://doi.org/10.1109/MSP.2020.2975749.
    19. H. Guo, H. Huang, X. Chen, H. Zhao, and Y. Wang, "Audio deepfake detection with self-supervised WavLM and multi-fusion attentive classifi-er," Dec. 2023. [Online]. Available: https://arxiv.org/abs/2312.08089.

  • Downloads

  • How to Cite

    Rani, R., & Kishan , B. . (2025). Comparative Analysis Of ML/DL Models for ‎Voice Spoofing Detection. International Journal of Basic and Applied Sciences, 14(5), 20-25. https://doi.org/10.14419/ct23r415