DCASE 2018 Challenge Surrey Cross-Task convolutional neural network baseline
This provides a standardized baseline for researchers in audio processing, but it is incremental as it applies existing CNN architectures to new tasks.
The paper tackled the problem of creating a cross-task baseline system for five audio classification and sound event detection tasks in the DCASE 2018 Challenge, using convolutional neural networks (CNNs) with 4 and 8 layers, and found that the 8-layer CNN generally performed better, achieving accuracies such as 0.680 on Task 1 and 0.895 on Task 2.
The Detection and Classification of Acoustic Scenes and Events (DCASE) consists of five audio classification and sound event detection tasks: 1) Acoustic scene classification, 2) General-purpose audio tagging of Freesound, 3) Bird audio detection, 4) Weakly-labeled semi-supervised sound event detection and 5) Multi-channel audio classification. In this paper, we create a cross-task baseline system for all five tasks based on a convlutional neural network (CNN): a "CNN Baseline" system. We implemented CNNs with 4 layers and 8 layers originating from AlexNet and VGG from computer vision. We investigated how the performance varies from task to task with the same configuration of neural networks. Experiments show that deeper CNN with 8 layers performs better than CNN with 4 layers on all tasks except Task 1. Using CNN with 8 layers, we achieve an accuracy of 0.680 on Task 1, an accuracy of 0.895 and a mean average precision (MAP) of 0.928 on Task 2, an accuracy of 0.751 and an area under the curve (AUC) of 0.854 on Task 3, a sound event detection F1 score of 20.8% on Task 4, and an F1 score of 87.75% on Task 5. We released the Python source code of the baseline systems under the MIT license for further research.