Technology Category
Machine Learning: Information TheoryCognitive Modeling & Cognitive Systems: Other Foundations of Cognitive Modeling & SystemsReasoning under Uncertainty: Stochastic Optimization
Toward Optimal ANC: Establishing Mutual Information Lower Bound
🤖 AI Summary
Active noise cancellation (ANC) lacks a theoretically grounded performance upper bound, hindering objective evaluation of deep learning–based improvements. Method: This work establishes, for the first time, an information-theoretic lower bound on normalized mean square error (NMSE) for ANC—comprising an information-theoretic component (quantifying how well the anti-noise signal captures the entropy of the disturbance) and a support-set component (characterizing physically uncontrollable frequency bands in the acoustic path). The bound is derived via mutual information quantification, support-set modeling, and rigorous theoretical analysis, and empirically validated on the NOISEX dataset. Contribution/Results: The proposed bound is tight and robust to reverberation, providing the first computable, interpretable, and physically meaningful performance benchmark for deep ANC—unifying algorithmic information-processing capability with fundamental system-level physical constraints.
Technology Category
Application Category
📝 Abstract
Active Noise Cancellation (ANC) algorithms aim to suppress unwanted acoustic disturbances by generating anti-noise signals that destructively interfere with the original noise in real time. Although recent deep learning-based ANC algorithms have set new performance benchmarks, there remains a shortage of theoretical limits to rigorously assess their improvements. To address this, we derive a unified lower bound on cancellation performance composed of two components. The first component is information-theoretic: it links residual error power to the fraction of disturbance entropy captured by the anti-noise signal, thereby quantifying limits imposed by information-processing capacity. The second component is support-based: it measures the irreducible error arising in frequency bands that the cancellation path cannot address, reflecting fundamental physical constraints. By taking the maximum of these two terms, our bound establishes a theoretical ceiling on the Normalized Mean Squared Error (NMSE) attainable by any ANC algorithm. We validate its tightness empirically on the NOISEX dataset under varying reverberation times, demonstrating robustness across diverse acoustic conditions.
Problem
Research questions and friction points this paper is trying to address.
Establish theoretical limits for ANC algorithm performance
Quantify information-processing constraints in noise cancellation
Measure irreducible error from physical cancellation limitations
Innovation
Methods, ideas, or system contributions that make the work stand out.
Derives unified lower bound for ANC performance
Combines information-theoretic and support-based components
Validates bound empirically on NOISEX dataset
🔎 Similar Papers
2024-10-10arXiv.orgCitations: 0
