Brief

Researchers have identified a critical ambiguity in applying randomized smoothing for audio classification robustness certification. The standard method assumes noise is added in a single vector space, but audio processing often involves multiple transformations, making the certified object unclear. The study demonstrates that different representations, such as raw waveforms versus log-mel features, and preprocessing steps like normalization, significantly alter the robustness certification results. The authors recommend explicit reporting of the certified object, perturbation model, and post-noise geometry changes for accurate and reproducible audio robustness studies. AI

Researchers have developed Perforated Neural Networks, a novel approach to optimizing models for edge devices. This technique, which involves adding artificial Dendrite Nodes to standard convolutional neural networks, was successfully applied to keyword spotting on the Edge Impulse platform. The resulting dendritic models demonstrated superior performance, achieving higher accuracy with significantly fewer parameters compared to traditional architectures, suggesting a promising new tool for efficient edge AI deployment. AI