A new phase-based feature representation for robust speech recognition.
Erfan LoweimiSeyed Mohammad AhadiThomas DrugmanPublished in: ICASSP (2013)
Keyphrases
- speech recognition
- feature representation
- noisy environments
- feature descriptors
- hidden markov models
- language model
- speech synthesis
- pattern recognition
- speech signal
- speech recognizer
- low dimensional
- speech recognition technology
- speaker identification
- automatic speech recognition
- speech recognition systems
- feature extraction
- sparse representation
- face recognition
- speaker independent
- speaker dependent
- machine learning
- feature set
- d objects
- image analysis
- image sequences
- speaker adaptation