Detection of Cross-Dataset Fake Audio Based on Prosodic and Pronunciation Features.
Chenglong WangJiangyan YiJianhua TaoChu Yuan ZhangShuai ZhangXun ChenPublished in: CoRR (2023)
Keyphrases
- feature set
- false positives
- speech recognition
- benchmark datasets
- object detection
- low level
- detection method
- feature extraction
- classification accuracy
- cepstral features
- personal photos
- text to speech
- extracted features
- context sensitive
- automatic detection
- event detection
- visual information
- detection algorithm
- signal processing
- image features
- feature vectors
- feature space