Detection of Cross-Dataset Fake Audio Based on Prosodic and Pronunciation Features.
Chenglong WangJiangyan YiJianhua TaoChu Yuan ZhangShuai ZhangXun ChenPublished in: INTERSPEECH (2023)
Keyphrases
- feature set
- speech recognition
- low level
- multimedia
- false positives
- benchmark datasets
- feature extraction
- automatic detection
- image features
- feature space
- audio features
- detection method
- object detection
- classification accuracy
- event detection
- adaboost classifier
- visual features
- visual information
- extracted features
- cepstral features