CoNSIST: Consist of New Methodologies on AASIST for Audio Deepfake Detection 


Vol. 13,  No. 10, pp. 513-519, Oct.  2024
https://doi.org/10.3745/TKIPS.2024.13.10.513


PDF
  Abstract

Advancements in artificial intelligence(AI) have significantly improved deep learning-based audio deepfake technology, which has been exploited for criminal activities. To detect audio deepfake, we propose CoNSIST, an advanced audio deepfake detection model. CoNSIST builds on AASIST, which a graph-based end-to-end model, by integrating three key components: Squeeze and Excitation, Positional Encoding, and Reformulated HS-GAL. These additions aim to enhance feature extraction, eliminate unnecessary operations, and incorporate diverse information. Our experimental results demonstrate that CoNSIST significantly outperforms existing models in detecting audio deepfakes, offering a more robust solution to combat the misuse of this technology

  Statistics


  Cite this article

[IEEE Style]

J. H. Ha, J. W. Mun, S. Y. Lee, "CoNSIST: Consist of New Methodologies on AASIST for Audio Deepfake Detection," The Transactions of the Korea Information Processing Society, vol. 13, no. 10, pp. 513-519, 2024. DOI: https://doi.org/10.3745/TKIPS.2024.13.10.513.

[ACM Style]

Jae Hoon Ha, Joo Won Mun, and Sang Yup Lee. 2024. CoNSIST: Consist of New Methodologies on AASIST for Audio Deepfake Detection. The Transactions of the Korea Information Processing Society, 13, 10, (2024), 513-519. DOI: https://doi.org/10.3745/TKIPS.2024.13.10.513.