Statistical normalisation of phase-based feature representation for robust speech recognition.
Erfan LoweimiJon BarkerThomas HainPublished in: ICASSP (2017)
Keyphrases
- speech recognition
- feature representation
- noisy environments
- language model
- feature descriptors
- hidden markov models
- speech recognizer
- feature extraction
- pattern recognition
- speech synthesis
- speech recognition technology
- speaker identification
- speaker independent
- speech signal
- face recognition
- sparse representation
- automatic speech recognition
- low dimensional
- co occurrence
- speech recognition systems
- probabilistic model
- training data
- image segmentation
- speaker dependent
- information retrieval