Cross-Covariance-based Features for Speech Classification in Film Audio.
Matthew BenatanKia NgPublished in: DMS (2015)
Keyphrases
- feature set
- classification accuracy
- feature vectors
- mel frequency cepstral coefficients
- feature extraction
- classification method
- classification models
- speaker identification
- feature space
- acoustic signals
- audio features
- svm classifier
- emotion classification
- speech recognition
- extracted features
- classification process
- multimedia
- pattern recognition
- spectral features
- cepstral features
- extracting features
- linear predictive coding
- audio visual
- training set
- class labels
- high dimensionality
- text classification
- classification algorithm
- genre classification
- support vector
- decision trees
- feature values
- feature analysis
- benchmark datasets
- image classification
- feature representation
- speech signal
- text to speech
- feature selection
- acoustic features
- support vector machine
- audio stream
- speech music discrimination
- hidden markov models
- visual speech
- image features
- speaker recognition
- supervised learning
- broadcast news
- weak classifiers