Piotr Kawa

speaker verification (3) neural network (2) audio deepfake detection (2) deepfake detection (2) attention mechanism (1) weakly supervised learning (1) speech recognition (1) automatic speech recognition (1) adversarial training (1) adversarial attack (1) text-to-speech synthesis (1) weakly supervised semantic segmentation (1) audio deepfake (1) mel spectrogram (1) audio forensics (1) attention decoder (1) voice authenticity (1) voice edit detection (1) fake speech detection (1) face anti-spoofing (1)