Precision-Varying Prediction (PVP): Robustifying ASR systems against adversarial attacks

Documenti analoghi

• DistriBlock: Identifying adversarial audio samples by leveraging characteristics of the output distribution
  di: Pizarro, Matías, et al.
  Pubblicazione: (2023)
• Lightweight Model Attribution and Detection of Synthetic Speech via Audio Residual Fingerprints
  di: Pizarro, Matías, et al.
  Pubblicazione: (2024)
• Robustifying automatic speech recognition by extracting slowly varying features
  di: Pizarro, Matías, et al.
  Pubblicazione: (2021)
• Malacopula: adversarial automatic speaker verification attacks using a neural-based generalised Hammerstein model
  di: Todisco, Massimiliano, et al.
  Pubblicazione: (2024)
• Comparative Study on Noise-Augmented Training and its Effect on Adversarial Robustness in ASR Systems
  di: Pizzi, Karla, et al.
  Pubblicazione: (2024)