Embedding Physical Augmentation and Wavelet Scattering Transform to Generative Adversarial Networks for Audio Classification with Limited Training Resources.
Kah Kuan TehTran Huy DatPublished in: ICASSP (2019)
Keyphrases
- training set
- training process
- pattern recognition
- classification accuracy
- training phase
- multimedia
- supervised learning
- feature vectors
- discriminative classifiers
- discriminative learning
- limited resources
- training samples
- discriminative training
- classification algorithm
- image classification
- signal processing
- unsupervised learning
- resource allocation
- multi layer perceptron
- denoising
- machine learning
- wavelet transform
- multiresolution
- multiscale
- social networks
- wavelet features
- feature selection
- image processing
- decision trees
- feature extraction
- multi agent
- network structure
- support vector machine svm
- support vector machine
- support vector
- wavelet coefficients
- class labels
- text classification