This repository includes the code and notebooks for generating the data and running the experiments reported in
Pablo Zinemanas, Pablo Cancela and Martín Rocamora. MAVD: a dataset for sound event detection in urban environments. DCASE 2019 Workshop.
The repository has the following folders:
- mavd --> Main source files for data generation, network model and callbacks.
- exps --> Folders with files of each experiment (weights, logs, results).
- notebooks --> Jupyter notebooks for running the experiments.
- utils --> Some useful scripts to work with the dataset.