Documenti analoghi

• Study of Pre-processing Defenses against Adversarial Attacks on State-of-the-art Speaker Recognition Systems
  di: Joshi, Sonal, et al.
  Pubblicazione: (2021)
• SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline
  di: Wang, Helin, et al.
  Pubblicazione: (2025)
• DiT-Flow: Speech Enhancement Robust to Multiple Distortions based on Flow Matching in Latent Space and Diffusion Transformers
  di: Cao, Tianyu, et al.
  Pubblicazione: (2026)
• Noise-robust Speech Separation with Fast Generative Correction
  di: Wang, Helin, et al.
  Pubblicazione: (2024)
• Unraveling Adversarial Examples against Speaker Identification -- Techniques for Attack Detection and Victim Model Classification
  di: Joshi, Sonal, et al.
  Pubblicazione: (2024)