Multiscale Audio Spectrogram Transformer for Efficient Audio Classification.
Wentao ZhuMohamed OmarPublished in: CoRR (2023)
Keyphrases
- multiscale
- multimedia
- decision trees
- music genre classification
- pattern analysis
- acoustic signals
- feature extraction
- visual information
- signal processing
- pattern recognition
- fuzzy logic
- audio signals
- feature vectors
- audio video
- automatic music genre classification
- visual data
- audio visual
- supervised learning
- classification accuracy
- feature selection
- audio stream
- neural network
- multimedia information
- class labels
- speech music discrimination
- emotion recognition
- classification models
- support vector
- classification scheme
- multi modal
- extracted features
- pattern classification
- support vector machine svm
- text classification
- wavelet transform
- multi class
- support vector machine
- expert systems
- feature space
- machine learning