Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition.
Chun-Fu (Richard) ChenQuanfu FanNeil MallinarTom SercuRogério Schmidt FerisPublished in: ICLR (Poster) (2019)
Keyphrases
- speech recognition
- feature representation
- multiscale
- hidden markov models
- language model
- feature extraction
- speech signal
- face recognition
- speech synthesis
- low dimensional
- noisy environments
- automatic speech recognition
- speech recognition systems
- speech recognition technology
- speech recognizer
- pattern recognition
- feature set
- sparse representation
- speaker identification
- speaker independent
- image segmentation
- natural images
- visual information
- image representation
- visual features
- edge detection
- low level
- image processing
- nearest neighbor
- feature vectors