Multiscale Audio Spectrogram Transformer for Efficient Audio Classification.
Wentao ZhuMohamed OmarPublished in: ICASSP (2023)
Keyphrases
- multiscale
- multimedia
- pattern recognition
- audio signals
- pattern analysis
- acoustic signals
- music genre classification
- learning algorithm
- image classification
- signal processing
- classification accuracy
- classification scheme
- audio video
- audio visual
- feature selection
- automatic music genre classification
- pattern classification
- support vector machine
- audio recordings
- image processing
- audio features
- genre classification
- visual data
- machine learning
- visual information
- classification method
- classification algorithm
- feature vectors
- support vector
- decision trees
- neural network
- power system
- support vector machine svm
- supervised learning
- speaker identification
- fuzzy logic
- hidden markov models
- feature extraction