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得到广泛应用，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）技术在基于学习的端到端语音源定位模型中的应用。我们采用层相关性传播（LRP）技术，旨在确定输入中哪些部分对输出预测更重要。通过LRP，我们分析了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到声源的笛卡尔坐标），重点关注两个模型输入特征的相关性。研究发现，两个网络均通过降噪和去混响处理麦克风信号，以计算更精确的统计相关性，从而实现声源定位。为进一步验证这一事实，我们利用两个网络提取的麦克风信号和相关性信号，通过广义互相关-相位变换（GCC-PHAT）估计到达时间差（TDoAs），并证明后者能获得更精确的时延估计结果。