用户可自定义麦克风方向性模式，实时实现精准音频空间滤波。
Neural Directional Filtering with Configurable Directivity Pattern at Inference
- 用FiLM结构让神经网络根据用户输入动态调整方向性
- 能泛化到未见过的复杂形状方向性，且抗干扰能力强
- 适合需要灵活声场控制的语音采集与会议系统
空间滤波在诸多音频应用中具有优势。本文提出一种用户可定义方向性模式的神经方向滤波（UNDF），使空间滤波能够基于用户在推理时定义的方向性模式进行。为此，我们设计了一种集成特征逐维线性调制（FiLM）的深度神经网络架构，使用户定义的模式作为条件输入。通过分析表明，该架构使UNDF在推理时能泛化至未见过的方向性模式，具备更高的方向性、对尺度变化和入射方向变化的鲁棒性。此外，我们逐步优化训练策略，提升模式逼近能力，使UNDF可拟合不规则形状。实验对比显示，UNDF优于传统方法。
原文摘要 · Abstract (English)
Spatial filtering with a desired directivity pattern is advantageous for many audio applications. In this work, we propose neural directional filtering with user-defined directivity patterns (UNDF), which enables spatial filtering based on directivity patterns that users can define during inference. To achieve this, we propose a DNN architecture that integrates feature-wise linear modulation (FiLM), allowing user-defined patterns to serve as conditioning inputs. Through analysis, we demonstrate that the FiLM-based architecture enables the UNDF to generalize to unseen user-defined patterns during interference with higher directivities, scaling variations, and different steering directions. Furthermore, we progressively refine training strategies to enhance pattern approximation and enable UNDF to approximate irregular shapes. Lastly, experimental comparisons show that UNDF outperforms conventional methods.
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。