Visual features for context-aware speech recognition.
Abhinav GuptaYajie MiaoLeonardo NevesFlorian MetzePublished in: ICASSP (2017)
Keyphrases
- speech recognition
- context aware
- visual features
- contextual information
- image classification
- language model
- visual content
- visual information
- pattern recognition
- hidden markov models
- low level
- image annotation
- image search
- automatic speech recognition
- mobile devices
- image retrieval
- keywords
- speech signal
- noisy environments
- low level features
- semantic concepts
- speech recognition systems
- image collections
- key frames
- probabilistic model
- video shots
- object recognition