Audio Deepfake Detection
Audio deepfake detection aims to identify artificially generated audio, combating the spread of misinformation and fraudulent activities. Current research focuses on developing robust models, often employing transformer-based architectures and leveraging techniques like contrastive learning and one-class learning, to improve accuracy and generalization across diverse deepfake generation methods. This field is crucial for safeguarding against malicious uses of synthetic audio, with ongoing efforts concentrating on improving model robustness against manipulation attacks and enhancing detection in real-world, noisy conditions. The development of standardized datasets and evaluation benchmarks is also a key area of focus to facilitate more reliable comparisons and progress in the field.
Papers
Toward Robust Real-World Audio Deepfake Detection: Closing the Explainability Gap
Georgia Channing, Juil Sock, Ronald Clark, Philip Torr, Christian Schroeder de Witt
Learn from Real: Reality Defender's Submission to ASVspoof5 Challenge
Yi Zhu, Chirag Goel, Surya Koppisetti, Trang Tran, Ankur Kumar, Gaurav Bharaj