Audio-visual speech synthesis for finnish.
Jean-Luc OlivesRiikka MöttönenJanne KuljuMikko SamsPublished in: AVSP (1999)
Keyphrases
- audio visual
- speech synthesis
- speech recognition
- multi modal
- text to speech
- visual information
- vocal tract
- visual data
- multimedia
- emotion recognition
- audio visual speech recognition
- person authentication
- multi stream
- low level
- speaker verification
- automatic speech recognition
- temporal context
- information retrieval
- feature extraction
- three dimensional
- image processing