Deep learning models are widely applied in the signal processing community, yet their inner working procedure is often treated as a black box. In this paper, we investigate the use of eXplainable Artificial Intelligence (XAI) techniques to learning-based end-to-end speech source localization models. We consider the Layer-wise Relevance Propagation (LRP) technique, which aims to determine which parts of the input are more important for the output prediction. Using LRP we analyze two state-of-the-art models, of differing architectural complexity that map audio signals acquired by the microphones to the cartesian coordinates of the source. Specifically, we inspect the relevance associated with the input features of the two models and discover that both networks denoise and de-reverberate the microphone signals to compute more accurate statistical correlations between them and consequently localize the sources. To further demonstrate this fact, we estimate the Time-Difference of Arrivals (TDoAs) via the Generalized Cross Correlation with Phase Transform (GCC-PHAT) using both microphone signals and relevance signals extracted from the two networks and show that through the latter we obtain more accurate time-delay estimation results.

翻译：深度学习模型在信号处理领域被广泛应用，但其内部工作机制常被视为黑箱。本文研究可解释人工智能（XAI）技术在学习型端到端语音源定位模型中的应用。我们采用层级相关性传播（LRP）技术，旨在确定输入中对输出预测最重要的部分。通过LRP分析两个架构复杂度不同的先进模型，这些模型将麦克风采集的音频信号映射为声源的笛卡尔坐标。具体地，我们检查两个模型输入特征的相关性，发现两个网络均通过降噪和去混响处理麦克风信号，计算更精确的统计相关性，从而实现声源定位。为验证这一事实，我们分别基于两个网络的麦克风信号及其提取的相关性信号，采用广义互相关-相位变换（GCC-PHAT）方法估计到达时间差（TDoAs），结果表明后者能获得更精确的时延估计结果。