This code uses Recurrence Quantification Analysis (RQA) features for the task of Scene Classification. These features are computed over a thresholded similarity matrix computed from windows of MFCC features. Added to traditional MFCC statistics, they improve accuracy when using a standard SVM classifier.

Related publications

G. Roma, W. Nogueira, and P. Herrera, “Recurrence Quantification Analysis for auditory scene classification,” 2013.
[More Details] [BIBTEX] [URL (ext.)]