Temporal feature integration refers to a set of strategies attempting to capture the information\nconveyed in the temporal evolution of the signal. It has been extensively applied in the context\nof semantic audio showing performance improvements against the standard frame-based audio\nclassification methods. This paper investigates the potential of an enhanced temporal feature\nintegration method to classify environmental sounds. The proposed method utilizes newly introduced\nintegration functions that capture the texture window shape in combination with standard functions\nlike mean and standard deviation in a classification scheme of 10 environmental sound classes.\nThe results obtained from three classification algorithms exhibit an increase in recognition accuracy\nagainst a standard temporal integration with simple statistics, which reveals the discriminative ability\nof the new metrics.
Loading....