{"ID":2827458,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.16304","arxiv_id":"2512.16304","title":"CogSR: Semantic-Aware Speech Super-Resolution via Chain-of-Thought Guided Flow Matching","abstract":"Applying speech super-resolution (SR) to recordings with severely low sampling rates is a critical challenge in digital archiving and investigative audio recovery. In these scenarios, the input lacks essential acoustic cues. Consequently, existing generative models often fail; without sufficient context, they hallucinate phonetic content, guessing words based on probability rather than meaning. To address this, we propose CogSR, a framework designed specifically for high-precision, offline restoration. Our approach shifts the focus from simple signal mapping to cognitive reconstruction. By integrating a Large Audio-Language Model, we employ Chain-of-Thought reasoning to act as a semantic anchor, while explicit acoustic priors ensure the speaker's identity remains consistent. This guides a Rectified Flow backbone to synthesize high-frequency details that are not only realistic but linguistically accurate. Evaluations show that CogSR effectively eliminates ambiguity in severe degradation regimes, making it a robust solution for restoring high-value legacy and surveillance audio.","short_abstract":"Applying speech super-resolution (SR) to recordings with severely low sampling rates is a critical challenge in digital archiving and investigative audio recovery. In these scenarios, the input lacks essential acoustic cues. Consequently, existing generative models often fail; without sufficient context, they hallucina...","url_abs":"https://arxiv.org/abs/2512.16304","url_pdf":"https://arxiv.org/pdf/2512.16304v1","authors":"[\"Jiajun Yuan\",\"Xiaochen Wang\",\"Yuhang Xiao\",\"Yulin Wu\",\"Chenhao Hu\",\"Xueyang Lv\"]","published":"2025-12-18T08:46:21Z","proceeding":"cs.SD","tasks":"[\"cs.SD\"]","methods":"[\"Language Model\"]","has_code":false}