Comparing time and frequency domain for audio event recognition using deep learning.
Lars HertelHuy PhanAlfred MertinsPublished in: IJCNN (2016)
Keyphrases
- frequency domain
- deep learning
- spatial domain
- fourier transform
- unsupervised learning
- unsupervised feature learning
- cross correlation
- signal processing
- feature extraction
- machine learning
- subband
- denoising
- mental models
- weakly supervised
- power spectra
- image processing
- pattern recognition
- single image
- input image
- face recognition