用克罗内克积分解降低语音去混响的计算开销
Forward Convolutive Prediction for Frame Online Monaural Speech Dereverberation Based on Kronecker Product Decomposition
- 将长预测滤波器拆分为两个短滤波器的克罗内克积形式
- 在保持性能的同时，计算量显著降低
- 适合实时语音系统部署，尤其对资源受限场景友好
语音去混响是语音处理中的关键课题，旨在缓解语音通信与交互系统中混响带来的负面影响。现有方法中，前向卷积预测（FCP）因能有效预测直达信号并估计线性预测滤波器以抑制残余混响而受到关注。然而，该方法通常需要过长的线性预测滤波器，导致计算复杂度高。为此，本文提出一种基于克罗内克积（KP）分解的新型FCP方法，将长预测滤波器建模为两个更短滤波器的克罗内克积，显著降低计算成本。同时设计自适应算法在线迭代更新短滤波器。实验表明，相比传统方法，本方法在保持竞争性去混响性能的同时，大幅减少计算开销。
原文摘要 · Abstract (English)
Dereverberation has long been a crucial research topic in speech processing, aiming to alleviate the adverse effects of reverberation in voice communication and speech interaction systems. Among existing approaches, forward convolutional prediction (FCP) has recently attracted attention. It typically employs a deep neural network to predict the direct-path signal and subsequently estimates a linear prediction filter to suppress residual reverberation. However, a major drawback of this approach is that the required linear prediction filter is often excessively long, leading to considerable computational complexity. To address this, our work proposes a novel FCP method based on Kronecker product (KP) decomposition, in which the long prediction filter is modeled as the KP of two much shorter filters. This decomposition significantly reduces the computational cost. An adaptive algorithm is then provided to iteratively update these shorter filters online. Experimental results show that, compared to conventional methods, our approach achieves competitive dereverberation performance while substantially reducing computational cost.
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。