用Transformer直接生成降噪滤波器，无需分解重构
Transformer-based End-to-End Control Filter Generation for Active Noise Control
- Transformer直接端到端生成控制滤波器，无需分步设计
- 实测在真实噪声下降噪效果优于传统方法
- 适合需要自适应降噪的实时系统开发者
为解决现有生成式固定滤波主动降噪（GFANC）方法依赖滤波器分解与重构、需带标签数据监督学习的问题，本文提出基于Transformer的端到端控制滤波器生成（E2E-CFG）框架。该方法将协处理器与实时控制器整合为全可微的主动降噪系统，直接以累积误差信号作为训练目标，无需进行滤波器的分解-重构过程。通过摒弃该流程，新设计简化了控制链路，避免了误差累积。Transformer架构利用注意力机制有效捕捉全局与动态噪声特征。在真实录音噪声上的数值仿真表明，所提方法在不同噪声类型下均实现更优的降噪性能与适应性，优于原始GFANC框架。
原文摘要 · Abstract (English)
To address the limitations of existing Generative Fixed-Filter Active Noise Control (GFANC) methods, which rely on filter decomposition and recombination and require supervised learning with labeled data, this paper proposes a Transformer-based End-to-End Control-Filter Generation (E2E-CFG) framework. Unlike previous approaches that predict combination weights of sub control filters, the proposed method directly generates control filters in an unsupervised manner by integrating the co-processor and real-time controller into a fully differentiable ANC system, where the accumulated error signal is used as the training objective. By abandoning the decomposition--reconstruction process, the proposed design simplifies the control pipeline and avoids error accumulation, while the Transformer architecture effectively captures global and dynamic noise characteristics through its attention mechanism. Numerical simulations on real-recorded noises demonstrate that the proposed method achieves improved noise reduction performance and adaptability to different types of noises compared with the original GFANC framework.
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。