How Deep Are the Fakes? Focusing on Audio Deepfake: A Survey.
Zahra KhanjaniGabrielle WatsonVandana P. JanejaPublished in: CoRR (2021)
Keyphrases
- multimedia
- visual information
- cross modal
- audio signals
- machine learning
- signal processing
- music genre classification
- audio visual
- emotion recognition
- multimedia information
- audio features
- audio video
- cepstral features
- music scores
- digital audio
- text to speech
- audio signal
- visual data
- unsupervised learning
- low level
- learning algorithm