Speaker normalization for audio-visual articulation training.
Marcel OgnerZdravko KacicPublished in: EUROSPEECH (1999)
Keyphrases
- audio visual
- multi modal
- visual information
- speaker verification
- person authentication
- visual data
- multimedia
- multi stream
- audio visual speech recognition
- emotion recognition
- training set
- passage retrieval
- temporal context
- gaussian mixture model
- speech recognition
- audio features
- co occurrence
- image data
- three dimensional