Speech Recognition with Multi-modal Features Based on Neural Networks.
Myung-Won KimJoung Woo RyuEun Ju KimPublished in: ICONIP (2) (2006)
Keyphrases
- multi modal
- speech recognition
- neural network
- speech recognition systems
- pattern recognition
- hidden markov models
- language model
- cepstral coefficients
- speech processing
- speech signal
- speech synthesis
- feature vectors
- image annotation
- high dimensional
- automatic speech recognition
- audio visual
- feature extraction
- feature set
- multiple modalities
- speech recognizer
- speaker identification
- audio visual speech recognition
- speaker dependent
- speech recognition technology
- extracted features
- maximum likelihood
- similarity measure
- computer vision