Analysis and Recognition of NAM Speech Using HMM Distances and Visual Information.
Panikos HeracleousV.-A. TranTakayuki NagaiKiyohiro ShikanoPublished in: IEEE Trans. Speech Audio Process. (2010)
Keyphrases
- visual information
- audio visual
- recognition engine
- visual features
- hidden markov models
- visual content
- low level
- speech recognition
- visual cues
- automatic speech recognition systems
- speech signal
- databases
- eye movements
- multi stream
- textual information
- action recognition
- image processing
- machine learning
- low level features
- semantic information
- similarity measure
- scene segmentation
- computer vision
- visual information retrieval
- artificial intelligence