Audio-visual graphical models for speech processing.
John R. HersheyHagai AttiasNebojsa JojicTrausti T. KristjanssonPublished in: ICASSP (5) (2004)
Keyphrases
- audio visual
- graphical models
- speech processing
- signal processing
- speech recognition
- multi modal
- speaker identification
- natural language processing
- probabilistic model
- visual information
- audio features
- bayesian networks
- visual data
- multimedia
- artificial intelligence
- machine learning
- pattern recognition
- text mining
- information extraction
- image data
- gaussian mixture model
- sound source