Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition.
Chun-Fu ChenQuanfu FanNeil MallinarTom SercuRogério Schmidt FerisPublished in: CoRR (2018)
Keyphrases
- speech recognition
- feature representation
- multiscale
- hidden markov models
- feature extraction
- speech synthesis
- language model
- speech recognizer
- face recognition
- pattern recognition
- low dimensional
- automatic speech recognition
- speech signal
- sparse representation
- speaker identification
- feature set
- speech recognition systems
- speech recognition technology
- image representation
- noisy environments
- low level
- visual information
- edge detection
- high dimensional
- speaker independent
- visual features
- feature descriptors