Now showing items 1-2 of 2

    • Analysing the predictions of a CNN-based replay spoofing detection system 

      CHETTRI, B; MISHRA, S; STURM, B; BENETOS, E; 2018 IEEE Workshop on Spoken Language Technology (IEEE, 2018-12-18)
      Playing recorded speech samples of an enrolled speaker - "replay attack" - is a simple approach to bypass an automatic speaker verification (ASV) system. The vulnerability of ASV systems to such attacks has been acknowledged ...
    • GAN-based Generation and Automatic Selection of Explanations for Neural Networks 

      MISHRA, S; STOLLER, D; BENETOS, E; STURM, B; DIXON, S; SafeML ICLR 2019 Workshop (2019-05-06)
      One way to interpret trained deep neural networks (DNNs) is by inspecting characteristics that neurons in the model respond to, such as by iteratively optimising the model input (e.g., an image) to maximally activate ...