论文标题
使用具有混合数据输入特征的深神经网络的几何感知DOA估计
Geometry-aware DoA Estimation using a Deep Neural Network with mixed-data input features
论文作者
论文摘要
与基于模型的到达方向（DOA）估计算法不同，基于深度神经网络（DNN）的基于学习的DOA估计算法通常受到一种特定麦克风阵列几何形状的训练，在应用于不同阵列的几何形状时会导致性能差。在本文中，我们说明了导致这种敏感性的基于监督的基于学习的算法和基于模型的算法之间的基本差异。旨在设计一种基于学习的DOA估计算法，该算法很好地推广到不同的阵列几何形状，在本文中，我们提出了一种几何学意识到的DOA估计算法。该算法使用完全连接的DNN并将混合数据作为输入特征，即与相变最大化的广义交叉相关的时间和麦克风坐标是已知的。混响场景的实验结果证明了所提出的算法对不同阵列几何形状的灵活性，并表明所提出的算法优于基于模型的算法，例如具有相变的转化响应功率。
Unlike model-based direction of arrival (DoA) estimation algorithms, supervised learning-based DoA estimation algorithms based on deep neural networks (DNNs) are usually trained for one specific microphone array geometry, resulting in poor performance when applied to a different array geometry. In this paper we illustrate the fundamental difference between supervised learning-based and model-based algorithms leading to this sensitivity. Aiming at designing a supervised learning-based DoA estimation algorithm that generalizes well to different array geometries, in this paper we propose a geometry-aware DoA estimation algorithm. The algorithm uses a fully connected DNN and takes mixed data as input features, namely the time lags maximizing the generalized cross-correlation with phase transform and the microphone coordinates, which are assumed to be known. Experimental results for a reverberant scenario demonstrate the flexibility of the proposed algorithm towards different array geometries and show that the proposed algorithm outperforms model-based algorithms such as steered response power with phase transform.
