Text-independent speaker verification using automatically labelled acoustic segments.
Dijana Petrovska-DelacrétazJan CernockýJean HennebertGérard CholletPublished in: ICSLP (1998)
Keyphrases
- speaker verification
- acoustic features
- prosodic features
- speaker recognition
- noisy environments
- text to speech
- audio visual
- information retrieval
- language identification
- keywords
- multilayer perceptron
- using artificial neural networks
- face verification
- gaussian mixture model
- multi modal
- visual information
- noise reduction
- text mining
- video sequences
- image processing