School of Naval Architecture, Ocean and Energy Power Engineering, Wuhan University of Technology, Wuhan, 430063, Hubei, China.
School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, 430200, Hubei, China.
Sci Rep. 2023 Apr 3;13(1):5443. doi: 10.1038/s41598-023-32657-7.
This paper presents a sound source localization (SSL) model based on residual network and channel attention mechanism. The method takes the combination of log-Mel spectrogram and generalized cross-correlation phase transform (GCC-PHAT) as the input features, and extracts the time-frequency information by using the residual structure and channel attention mechanism, thus obtaining a better localizing performance. The residual blocks are introduced to extract deeper features, which can stack more layers for high-level features and avoid gradient vanishing or exploding at the same time. The attention mechanism is taken into account for the feature extraction stage in the proposed SSL model, which can focus on the most important information on the input features. We use the signals collected by microphone array to explore the performance of the model under different features, and find the most suitable input features of the proposed method. We compare our method with other models on public dataset. Experience results show a quite substantial improvement of sound source localizing performance.
本文提出了一种基于残差网络和通道注意力机制的声源定位（SSL）模型。该方法将对数梅尔频谱和广义互相关相位变换（GCC-PHAT）的组合作为输入特征，并通过残差结构和通道注意力机制提取时频信息，从而获得更好的定位性能。残差块用于提取更深层次的特征，这可以堆叠更多的层来获取更高层次的特征，同时避免梯度消失或爆炸。在提出的 SSL 模型中，注意力机制被用于特征提取阶段，这可以关注输入特征上最重要的信息。我们使用麦克风阵列收集的信号来探索模型在不同特征下的性能，并找到最适合该方法的输入特征。我们在公共数据集上与其他模型进行了比较。实验结果表明，声源定位性能有了相当大的提高。
