针对语音的周期性特性，提出新型波束成形滤波器，提升降噪效果。
Cyclic Multichannel Wiener Filter for Acoustic Beamforming
- 基于语音周期平稳模型设计多通道滤波器，利用谐频间相关性增强信号
- 在模拟数据上显著提升信干比（SI-SDR），MSE降低约1.8dB
- 适合对语音周期特性敏感的场景，如语音增强与远场拾音
声学波束成形模型通常假设语音信号在短时帧内为广义平稳过程。然而，有声语音更宜建模为周期平稳（CS）过程，其均值和自相关呈周期 $T_1$ 变化，其中 $α_1=1/T_1$ 对应元音基频。高阶谐波频率位于基频的整数倍处。本文提出一种从周期平稳模型推导出的循环多通道维纳滤波器（cMWF），该波束成形器利用信号各谐频间的谱相关性，进一步降低目标信号与处理后输入间的均方误差（MSE）。所提cMWF在MSE意义下最优，当目标为广义平稳时退化为传统MWF。模拟数据实验显示，在合成数据上显著提升比例不变信干比（SI-SDR），但对基频 $α_1$ 估计精度高度敏感，限制了其在真实数据上的表现。
原文摘要 · Abstract (English)
Acoustic beamforming models typically assume wide-sense stationarity of speech signals within short time frames. However, voiced speech is better modeled as a cyclostationary (CS) process, a random process whose mean and autocorrelation are $T_1$-periodic, where $α_1=1/T_1$ corresponds to the fundamental frequency of vowels. Higher harmonic frequencies are found at integer multiples of the fundamental. This work introduces a cyclic multichannel Wiener filter (cMWF) for speech enhancement derived from a cyclostationary model. This beamformer exploits spectral correlation across the harmonic frequencies of the signal to further reduce the mean-squared error (MSE) between the target and the processed input. The proposed cMWF is optimal in the MSE sense and reduces to the MWF when the target is wide-sense stationary. Experiments on simulated data demonstrate considerable improvements in scale-invariant signal-to-distortion ratio (SI-SDR) on synthetic data but also indicate high sensitivity to the accuracy of the estimated fundamental frequency $α_1$, which limits effectiveness on real data.
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。