LCANets++: Robust Audio Classification Using Multi-Layer Neural Networks with Lateral Competition

• Published in: 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) pp. 129 - 133
• Main Authors: Dibbo, Sayanton V., Moore, Juston S., Kenyon, Garrett T., Teti, Michael A.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 14.04.2024
• Subjects: Adversarial Machine Learning; Audio Classification; Encoding; Neural Networks; Perturbation methods; Robustness; Signal processing algorithms; Speech recognition; Task analysis; Training
• DOI: 10.1109/ICASSPW62465.2024.10627668

Audio classification aims at recognizing audio signals, including speech commands or sound events. However, current audio classifiers are susceptible to perturbations and adversarial attacks. In addition, real-world audio classification tasks often suffer from limited labeled data. To help bridge these gaps, previous work developed neuro-inspired convolutional neural networks (CNNs) with sparse coding via the Locally Competitive Algorithm (LCA) in the first layer (i.e., LCANets) for computer vision. LCANets learn in a combination of supervised and unsupervised learning, reducing dependency on labeled samples. Motivated by the fact that auditory cortex is also sparse, we extend LCANets to audio recognition tasks and introduce LCANets++, which are CNNs that perform sparse coding in multiple layers via LCA. We demonstrate that LCANets++ are more robust than standard CNNs and LCANets against perturbations, e.g., background noise, as well as black-box and white-box attacks, e.g., evasion and fast gradient sign (FGSM) attacks.