PRIME-ANC：基于路径比信息建模的有源噪声控制高效神经滤波器合成
PRIME-ANC: Path-Ratio-Informed Modeling for Efficient Neural Filter Synthesis in Active Noise Control
浏览论文内容
中文总结 AI 辅助
PRIME-ANC通过神经合成器学习路径依赖修正，高效生成有源噪声控制FIR滤波器，在多个数据集上实现显著降噪并接近最优设计。
中文摘要 AI 辅助
听者声学特性的变化要求有源噪声控制（ANC）滤波器针对新的声学路径重新设计。我们提出PRIME-ANC，一种共享神经合成器，它学习一个有界的、依赖路径的对数幅度修正，应用于正则化的路径比基。最小相位重构和截断产生有限脉冲响应（FIR）滤波器；训练优化其噪声控制性能。在每数据集十次随机训练/测试划分中，PRIME-ANC在十路径数据集和公共耳机电声数据库上分别实现了50 Hz-5 kHz范围内平均保留的三分之一倍频程降噪18.81 dB和17.76 dB。在原始耳机测量上，它比路径比基改善了7.89 dB。消融研究支持解析基和路径依赖修正的贡献。给定校准的保留听者条件路径，PRIME-ANC无需迭代优化即可生成特定路径的FIR。经过三次Gauss-Newton更新，它达到21.43 dB降噪，接近直接加权最小二乘设计，同时产生更低的放大和均方根控制输出。
英文摘要
Changes in listener acoustics require active noise control (ANC) filters to be redesigned for new acoustic paths. We introduce PRIME-ANC, a shared neural synthesizer that learns a bounded, path-dependent logmagnitude correction to a regularized path-ratio base. Minimum-phase reconstruction and truncation produce finite-impulse-response (FIR) filters; training optimizes their noise-control performance. Across ten random training/test splits per dataset, PRIME-ANC achieves average held-out one-third-octave reductions of 18.81 and 17.76 dB over 50 Hz-5 kHz on a ten-path dataset and a public earphone database, respectively. On original earphone measurements, it improves upon the path-ratio base by 7.89 dB. Ablation studies support the contributions of both the analytic base and the path-dependent correction. Given calibrated paths for a held-out listener condition, PRIME-ANC generates a path-specific FIR without iterative optimization. With three Gauss-Newton updates, it reaches 21.43 dB reduction, approaching direct weighted least-squares design while producing lower amplification and root-mean-square control output.
发表机构
- Soochow University（苏州大学）
机构由 AI 辅助整理，请以论文原文为准。
