A statistical approach to assessing speech and voice variability in speaker verification.
Klaus R. SchererDidier GrandjeanTom JohnstoneGudrun KlasmeyerTanja BänzigerPublished in: INTERSPEECH (2003)
Keyphrases
- speaker verification
- prosodic features
- emotion recognition
- speaker recognition
- noisy environments
- audio visual
- acoustic features
- mel frequency cepstral coefficients
- text to speech
- speech synthesis
- facial expressions
- face verification
- multi modal
- multilayer perceptron
- speech quality
- information retrieval
- probabilistic neural network
- emotional state
- noise reduction
- human computer interaction
- image classification
- probabilistic model
- high dimensional