Aug 2026
Adaptive data-driven audio network for speech deepfake detection
This work proposes the adaptive data-driven audio network, which identifies the sparse coefficients for the input audio patches and updates the filters to better align with the data and reduces computational time to one-third of the network algorithms with Sinc filters.
Poline Xian, Che-Er Cheung, Jiaxi Ying et al.
· Journal of the Acoustical So... · 0 citations