Audio-visual multilevel fusion for speech and speaker recognition.
Girija ChettyMichael WagnerPublished in: INTERSPEECH (2008)
Keyphrases
- audio visual
- speaker recognition
- speaker verification
- multi modal
- visual information
- speaker identification
- audio features
- emotion recognition
- visual data
- multi stream
- acoustic features
- information fusion
- vector quantization
- gaussian mixture model
- multimedia
- probabilistic neural network
- speech signal
- context aware
- maximum likelihood
- image processing