AUCO ResNet: an end-to-end network for Covid-19 pre-screening from cough and breath

Highlights：

• The Auditory Cortex ResNet, briefly AUCO ResNet, is proposed and tested. It is a deep neural network architecture especially designed for audio classification trained end-to-end. It is inspired by the architectural organization of rat's auditory cortex, containing also innovations 2 and 3. The network outperforms the state-of-the-art accuracies on a reference audio benchmark dataset without any kind of preprocessing, imbalanced data handling and, most importantly, any kind of data augmentation.

• A trainable Mel-like spectrogram layer able to finetune the Mel-like-Spectrogram for capturing relevant time frequency information.

• A novel sinusoidal learnable attention mechanism which can be considered as a technique to weight local and global feature descriptors focusing on high frequency details.

• State of the art cross-dataset testing and related accuracies.