Neural Steerer:利用频率与声源位置上的因果神经场合成新型导向矢量
Neural Steerer: Novel Steering Vector Synthesis with a Causal Neural Field over Frequency and Source Positions
AI总结:
本文提出 neural steerer,用融合频率、方向、通道间相位差及因果正则化的连续复值神经场插值实测无响导向矢量,减少声源分离与定位所需测量。
摘要:
我们研究如何利用一个称为神经场的深度学习框架,对实测的无响导向矢量进行精确插值。该任务对于减少精确声源分离与定位所需的高资源测量具有关键作用,而声源分离与定位是语音识别前端不可或缺的部分。传统插值方法依赖于在固定、离散频率集合上对空间邻近测量值进行线性加权。受计算机视觉中神经场在新视角合成方面成功的启发,我们提出 neural steerer,这是一个连续的复值函数,以频率和方向作为输入,并生成相应的导向矢量。重要的是,该方法融入了通道间相位差信息,并加入一个强制滤波器因果性的正则化项,这对于精确的导向矢量建模至关重要。我们使用一个包含真实实测导向矢量的数据集开展实验,结果表明,我们的无分辨率模型能够有效插值此类测量数据。
英文摘要:
We address the problem of accurately interpolating measured anechoic steering vectors with a deep learning framework called the neural field. This task plays a pivotal role in reducing the resource-intensive measurements required for precise sound source separation and localization, essential as the front-end of speech recognition. Classical approaches to interpolation rely on linear weighting of nearby measurements in space on a fixed, discrete set of frequencies. Drawing inspiration from the success of neural fields for novel view synthesis in computer vision, we introduce the neural steerer, a continuous complex-valued function that takes both frequency and direction as input and produces the corresponding steering vector. Importantly, it incorporates inter-channel phase difference information and a regularization term enforcing filter causality, essential for accurate steering vector modeling. Our experiments, conducted using a dataset of real measured steering vectors, demonstrate the effectiveness of our resolution-free model in interpolating such measurements.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。