Speech Recognition by Integrating Audio, Visual and Contextual Features Based on Neural Networks.
Myung-Won KimJoung Woo RyuEun Ju KimPublished in: ICNC (2) (2005)
Keyphrases
- audio visual
- speech recognition
- contextual features
- audio visual speech recognition
- neural network
- pattern recognition
- multi modal
- multi stream
- hidden markov models
- contextual information
- conditional random fields
- visual information
- visual data
- language model
- automatic speech recognition
- speech signal
- audio features
- speaker verification
- temporal context
- multimedia
- noisy environments
- high dimensional
- speaker identification
- named entities
- image processing
- data mining
- natural language processing
- digit recognition