Dialect-based speaker classification using speaker-invariant dialect features.
Xuebin MaRuiyuan XuNobuaki MinematsuYu QiaoKeikichi HiroseAijun LiPublished in: ISCSLP (2010)
Keyphrases
- feature vectors
- classification accuracy
- feature set
- feature extraction
- feature space
- classification process
- extracted features
- classification models
- mel frequency cepstral coefficients
- svm classifier
- classification method
- audio visual
- speaker recognition
- speech recognition
- feature selection
- support vector machine
- speaker identification
- gender classification
- extracting features
- benchmark datasets
- feature values
- feature weights
- speaker verification
- support vector
- feature analysis
- invariant features
- feature representation
- feature selection algorithms
- decision trees
- features extraction
- image classification
- pattern recognition
- feature subset
- training set
- feature reduction
- low level
- class labels
- visual speech
- text classification
- invariant moments
- machine learning
- spectral features
- fourier descriptors
- automatic speech recognition
- high dimensionality
- texture features
- machine learning algorithms
- model selection
- supervised learning
- image features