Comparison of MPEG-7 audio spectrum projection features and MFCC applied to speaker recognition, sound classification and audio segmentation.
Hyoung-Gook KimThomas SikoraPublished in: ICASSP (5) (2004)
Keyphrases
- mel frequency cepstral coefficients
- speaker recognition
- speaker identification
- gaussian mixture model
- acoustic features
- feature set
- audio features
- feature vectors
- probabilistic neural network
- speech signal
- speaker verification
- speech recognition
- spectral features
- vector quantization
- audio signal
- extracting features
- feature extraction
- multimedia
- principal component analysis
- noisy environments
- feature selection
- speaker diarization
- classification accuracy
- extracted features
- feature space
- maximum likelihood
- image segmentation
- sound source
- em algorithm
- low level
- texture features
- pattern recognition
- neural network
- support vector machine svm
- mixture model