ASiT: Local-Global Audio Spectrogram Vision Transformer for Event Classification.
Sara Atito Ali AhmedMuhammad AwaisWenwu WangMark D. PlumbleyJosef KittlerPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2024)
Keyphrases
- pattern analysis
- pattern recognition
- class labels
- classification accuracy
- feature vectors
- pattern classification
- image classification
- support vector
- feature extraction
- multimedia
- computer vision
- classification systems
- automatic classification
- training set
- classification scheme
- vision system
- support vector machine svm
- benchmark datasets
- neural network
- classification models
- text classification
- signal processing
- decision trees
- real time
- classification algorithm
- fuzzy logic
- preprocessing
- extracted features
- music genre classification
- acoustic signals