analiza aiqbench
This study demonstrates that Randomized Smoothing (RS) certification in audio classification is highly sensitive to preprocessing choices like normalization and feature transformation, which can drastically alter effective perturbation norms. The authors argue that robustness claims are currently under-specified without explicitly defining the certified object and perturbation model, urging the community to adopt standardized reporting for waveform energies and post-noise geometry. For practitioners, this highlights the necessity of aligning smoothing protocols with specific task representations to avoid misleading robustness guarantees.
Representation Matters in Randomized Smoothing for Audio Classification
arXiv:2606.04210v1 Announce Type: cross Abstract: Randomized smoothing (RS) certifies robustness in the vector space where Gaussian noise is added. In audio classification, this space is often not uniquely defined as standard pipelines normalize, range-control, and transform waveforms into log-mel or other spectral features. We show that direct RS is therefore under-specified unless the certified object and preprocessing policy are explicit. On two audio benchmarks, keyword spotting and environmental-sound classification, we study waveform, feature-space, and post-processed smoothing. Our diagnostics show why representation-aware reporting is necessary: at the same smoothing level $\sigma=0.0025$, the two datasets share the same median raw radius $.007996$, but different waveform energies yield different SNR-equivalent scales ($83.98$ vs. $90.97$ dB); log-mel smoothing gives higher positive-radius certified accuracy on environmental sounds ($68.42\%$ vs. $65.53\%$), certifying more examples with nonzero radius but over features rather than waveforms; and clipping or peak normalization changes the effective perturbation norm by roughly $230$--$351\times$. We therefore recommend that audio RS studies choose and report the task-specific certified object and perturbation model, including the perturbation location, gain policy, raw radius, and any post-noise geometry changes.
Abstract:Randomized smoothing (RS) certifies robustness in the vector space where Gaussian noise is added. In audio classification, this space is often not uniquely defined as standard pipelines normalize, range-control, and transform waveforms into log-mel or other spectral features. We show that direct RS is therefore under-specified unless the certified object and preprocessing policy are explicit. On two audio benchmarks, keyword spotting and environmental-sound classification, we study waveform, feature-space, and post-processed smoothing. Our diagnostics show why representation-aware reporting is necessary: at the same smoothing level $\sigma=0.0025$, the two datasets share the same median raw radius $.007996$, but different waveform energies yield different SNR-equivalent scales ($83.98$ vs. $90.97$ dB); log-mel smoothing gives higher positive-radius certified accuracy on environmental sounds ($68.42\%$ vs. $65.53\%$), certifying more examples with nonzero radius but over features rather than waveforms; and clipping or peak normalization changes the effective perturbation norm by roughly $230$--$351\times$. We therefore recommend that audio RS studies choose and report the task-specific certified object and perturbation model, including the perturbation location, gain policy, raw radius, and any post-noise geometry changes.
Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Sound (cs.SD)
arXiv:2606.04210 [eess.AS]
(or arXiv:2606.04210v1 [eess.AS] for this version)
https://doi.org/10.48550/arXiv.2606.04210 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 276 cuvinte
Subiecte conexe
Hybrid Quantum-Classical NLP Classification with Compact Semantic Representations: An Experimental Analysis of Representation Compression
arXiv · 10 sept. 2026
Inference-Time Decision Calibration for Temporal Classification
arXiv · 16 iun. 2026
Sparse Prototype Code Underlies Classification and Prediction Across Modalities
arXiv · 19 aug. 2026
TIGER: Time-Series Classification with In-Context-Learning Gated Ensemble of Representations
arXiv · 6 oct. 2026