4 datasets found

Groups: Sound Recognition

Filter Results

  • ESC-10

    The ESC-10 dataset is a subset of the ESC-50 dataset with 10 classes and 400 recordings.

  • UrbanSound8k

    The UrbanSound8k dataset includes 8732 four-second length audio samples distributed in 10 classes: engine idling, car horn, children playing, drilling, air conditioner,...

  • ESC-50

    The dataset used for training the CNN in cough detection is composed of various modified audio clips gathered from open-source online sources. Each of these audio files...

  • From Sound Representation to Model Robustness

    This paper investigates the impact of different standard environmental sound representations (spectrograms) on the recognition performance and adversarial attack robustness of a...