{"ID":2829185,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.13905","arxiv_id":"2512.13905","title":"Ensemble-Guided Distillation for Compact and Robust Acoustic Scene Classification on Edge Devices","abstract":"We present a compact, quantization-ready acoustic scene classification (ASC) framework that couples an efficient student network with a learned teacher ensemble and knowledge distillation. The student backbone uses stacked depthwise-separable \"expand-depthwise-project\" blocks with global response normalization to stabilize training and improve robustness to device and noise variability, while a global pooling head yields class logits for efficient edge inference. To inject richer inductive bias, we assemble a diverse set of teacher models and learn two complementary fusion heads: z1, which predicts per-teacher mixture weights using a student-style backbone, and z2, a lightweight MLP that performs per-class logit fusion. The student is distilled from the ensemble via temperature-scaled soft targets combined with hard labels, enabling it to approximate the ensemble's decision geometry with a single compact model. Evaluated on the TAU Urban Acoustic Scenes 2022 Mobile benchmark, our approach achieves state-of-the-art (SOTA) results on the TAU dataset under matched edge-deployment constraints, demonstrating strong performance and practicality for mobile ASC.","short_abstract":"We present a compact, quantization-ready acoustic scene classification (ASC) framework that couples an efficient student network with a learned teacher ensemble and knowledge distillation. The student backbone uses stacked depthwise-separable \"expand-depthwise-project\" blocks with global response normalization to stabi...","url_abs":"https://arxiv.org/abs/2512.13905","url_pdf":"https://arxiv.org/pdf/2512.13905v1","authors":"[\"Hossein Sharify\",\"Behnam Raoufi\",\"Mahdy Ramezani\",\"Khosrow Hajsadeghi\",\"Saeed Bagheri Shouraki\"]","published":"2025-12-15T21:21:17Z","proceeding":"cs.SD","tasks":"[\"cs.SD\"]","methods":"[]","has_code":false}