Hierarchical speech recognition system using MFCC feature extraction and dynamic spiking RSOM.
Tarek BehiNajet ArousNoureddine EllouzePublished in: SNPD (2014)
Keyphrases
- feature extraction
- speech recognition
- speaker identification
- speech signal
- preprocessing
- pattern recognition
- feature vectors
- pattern classification
- linear predictive
- mel frequency cepstral coefficients
- face recognition
- bio inspired
- frequency domain
- image processing
- feed forward
- dynamic environments
- image classification
- feature set
- speaker recognition
- cepstral coefficients
- gaussian mixture model
- iris recognition
- extracting features
- principal component analysis