{"ID":2877233,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.20885","arxiv_id":"2508.20885","title":"SincQDR-VAD: A Noise-Robust Voice Activity Detection Framework Leveraging Learnable Filters and Ranking-Aware Optimization","abstract":"Voice activity detection (VAD) is essential for speech-driven applications, but remains far from perfect in noisy and resource-limited environments. Existing methods often lack robustness to noise, and their frame-wise classification losses are only loosely coupled with the evaluation metric of VAD. To address these challenges, we propose SincQDR-VAD, a compact and robust framework that combines a Sinc-extractor front-end with a novel quadratic disparity ranking loss. The Sinc-extractor uses learnable bandpass filters to capture noise-resistant spectral features, while the ranking loss optimizes the pairwise score order between speech and non-speech frames to improve the area under the receiver operating characteristic curve (AUROC). A series of experiments conducted on representative benchmark datasets show that our framework considerably improves both AUROC and F2-Score, while using only 69% of the parameters compared to prior arts, confirming its efficiency and practical viability.","short_abstract":"Voice activity detection (VAD) is essential for speech-driven applications, but remains far from perfect in noisy and resource-limited environments. Existing methods often lack robustness to noise, and their frame-wise classification losses are only loosely coupled with the evaluation metric of VAD. To address these ch...","url_abs":"https://arxiv.org/abs/2508.20885","url_pdf":"https://arxiv.org/pdf/2508.20885v1","authors":"[\"Chien-Chun Wang\",\"En-Lun Yu\",\"Jeih-Weih Hung\",\"Shih-Chieh Huang\",\"Berlin Chen\"]","published":"2025-08-28T15:14:39Z","proceeding":"cs.SD","tasks":"[\"cs.SD\"]","methods":"[]","has_code":false}