High-Resolution Speaker Counting in Reverberant Rooms Using CRNN with Ambisonics Features.
Pierre-Amaury GrumiauxSrdan KiticLaurent GirinAlexandre GuérinPublished in: EUSIPCO (2020)
Keyphrases
- high resolution
- prior knowledge
- high quality
- low level
- low resolution
- feature extraction
- svm classifier
- feature vectors
- image features
- neural network
- extracting features
- higher resolution
- high resolution images
- remote sensing
- super resolution
- feature set
- feature space
- video sequences
- multiscale
- training data
- feature selection