MFCC as Features for Speaker Classification using Machine Learning.
Xiaojie MuCheol-Hong MinPublished in: AIIoT (2023)
Keyphrases
- machine learning
- feature vectors
- feature extraction
- feature set
- mel frequency cepstral coefficients
- classification accuracy
- pattern recognition
- machine learning approaches
- speaker recognition
- classification method
- feature construction
- machine learning models
- decision trees
- machine learning methods
- classification process
- feature space
- extracted features
- support vector machine
- extracting features
- svm classifier
- text classification
- feature selection
- speech recognition
- benchmark datasets
- image classification
- classification models
- support vector machine svm
- gaussian mixture model
- feature level fusion
- probabilistic neural network
- model selection
- supervised learning
- feature generation
- pattern classification
- active learning
- low level
- spectral features
- feature analysis
- supervised machine learning
- machine learning algorithms
- speaker identification
- speaker verification
- image features
- principal component analysis
- acoustic features
- speaker diarization
- speech signal
- class labels
- unsupervised learning
- emotion classification
- partially supervised
- cepstral coefficients
- support vector
- structural features
- text mining
- supervised classification
- feature representation
- high dimensionality
- data mining
- false positives
- visual features