LCANets++: Robust Audio Classification using Multi-layer Neural Networks with Lateral Competition

August 23, 2023 ยท Declared Dead ยท ๐Ÿ› 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Sayanton V. Dibbo, Juston S. Moore, Garrett T. Kenyon, Michael A. Teti arXiv ID 2308.12882 Category cs.SD: Sound Cross-listed cs.CR, cs.LG, eess.AS Citations 7 Venue 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) Last Checked 3 months ago
Abstract
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Sound

Died the same way โ€” ๐Ÿ‘ป Ghosted