Audiovisual speech recognition using multiscale nonlinear image decomposition.
Iain A. MatthewsJ. Andrew BanghamStephen J. CoxPublished in: ICSLP (1996)
Keyphrases
- image decomposition
- multiscale
- audio visual
- emotion recognition
- scale space
- speech recognition
- coarse to fine
- image representation
- image segmentation
- speech signal
- natural images
- edge detection
- image denoising
- multi modal
- wavelet transform
- image processing
- endpoint detection
- visual information
- wavelet coefficients
- denoising
- image parsing
- wavelet domain
- multiscale analysis
- shape representation
- speech synthesis
- text to speech
- automatic speech recognition
- spoken language
- neural network
- recognition engine
- computer vision
- natural language
- object detection
- visual data
- image fusion
- multimedia content
- language model
- human computer interaction