Acoustic Scene Classification Using a CNN-SuperVector System Trained with Auditory and Spectrogram Image Features.
Rakib HyderShabnam GhaffarzadeganZhe FengJohn H. L. HansenTaufiq HasanPublished in: INTERSPEECH (2017)
Keyphrases
- scene classification
- image features
- image classification
- object recognition
- visual words
- image representation
- sound source
- indoor outdoor
- natural scenes
- gaussian mixture model
- biologically inspired
- image content
- scene recognition
- speech signal
- object categories
- computer vision
- bag of features
- bag of words
- feature vectors
- visual information
- scene representation
- natural images
- keypoints
- cross modal
- training set
- feature descriptors
- object classes
- multi modal
- object detection
- feature space
- multiscale
- pairwise
- texture features
- low level
- maximum likelihood
- scale space