On the vulnerability of speaker verification to realistic voice spoofing.
Serife Kucur ErgunayElie KhouryAlexandros LazaridisSébastien MarcelPublished in: BTAS (2015)
Keyphrases
- speaker verification
- emotion recognition
- prosodic features
- noisy environments
- speaker recognition
- face verification
- audio visual
- multilayer perceptron
- human computer interaction
- neural network
- using artificial neural networks
- sentiment analysis
- language identification
- information fusion
- multi modal
- facial expressions
- high dimensional
- information retrieval