An intelligent facial image coding driven by speech and phoneme.
Shigeo MorishimaKiyoharu AizawaHiroshi HarashimaPublished in: ICASSP (1989)
Keyphrases
- image coding
- speech recognition
- speech synthesis
- linear prediction
- automatic speech recognition
- automatic speech recognition systems
- speaker dependent
- filter bank
- wavelet transform
- speech signal
- visual speech
- hidden markov models
- image and video coding
- coding efficiency
- vector quantizer
- lapped transforms
- text to speech
- matching pursuit
- human faces
- facial expressions
- image coder
- face recognition
- bit plane
- language model
- speaker identification
- face images
- entropy constrained
- multiresolution
- image segmentation