用相位感知正则化修复音频量化失真，避免能量损失。
Audio dequantization using instantaneous frequency
- 引入相位感知正则化，保持时频域正弦分量的时序连续性
- 在SDR和PEMO-Q指标上优于当前最优方法，主观听感更自然
- 适合需要高保真音频重建的场景，如音乐修复与编解码
本文提出一种基于相位感知正则化的音频去量化方法（PHADQ），该正则化项最初成功应用于音频补全任务。该方法通过增强音频信号在时频表示中正弦分量的时序连续性，有效避免了传统L1正则化常导致的能量损失伪影。我们在SDR和PEMO-Q ODG客观指标下与现有最优方法对比，并进行了类MUSHRA的主观测试。结果表明，PHADQ在客观指标和主观听感上均表现更优，尤其在低比特率音频重建中展现出更强的鲁棒性。
原文摘要 · Abstract (English)
We present a dequantization method that employs a phase-aware regularizer, originally successfully applied in an audio inpainting problem. The method promotes a temporal continuity of sinusoidal components in time-frequency representation of the audio signal, and avoids energy loss artifacts commonly encountered with l1-based regularization approaches. The proposed method is called the Phase-Aware Audio Dequantizer (PHADQ). The method is evaluated against the state-of-the-art using the SDR and PEMO-Q ODG objective metrics, and a~subjective MUSHRA-like test.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。