Sparse Auditory Reproducing Kernel (SPARK) Features for Noise-Robust Speech Recognition.
Amin FazelShantanu ChakrabarttyPublished in: IEEE Trans. Speech Audio Process. (2012)
Keyphrases
- speech recognition
- noisy environments
- speech recognition systems
- hidden markov models
- automatic speech recognition
- speech signal
- language model
- pattern recognition
- speaker identification
- speech synthesis
- low level
- feature extraction
- feature set
- background noise
- classification accuracy
- image features
- computer vision
- signal processing
- high dimensional
- feature space
- training data
- speech recognizer