Dataset-AOB: urban sounds events classification

The dataset Dataset-AOB is an audio dataset collected and manually edited for urban sounds events classification using Convolutional Neural Networks for the Master Thesis: Ospina, A. "Audio Event Classification using Deep Learning. Use case: Urban Sounds Events classification with Convolutional Neural Networks," M.Eng. thesis, Beuth University of Applied Sciences, Berlin, 2020. - 10 audio events: alarm-siren, children playing, dog bark, engine, footsteps, glass breaking, gun shot, metro train, rain and screams. - duration: < 4 seconds - format: (.wav) - sampling rate: 22KHz - 44KHz - files: Dataset-AOB: development dataset (4831 samples), DatasetEVAL-AOB: evaluation (218 samples) - metadata: (.csv) - sources per class: (.png) Contact: [e-mail]