Environmental sound classification (ESC) is a challenging problem due to the unstructured spatial-temporal relations that exist in the sound signals. Recently, many studies have focused on abstracting features from convolutional neural networks while the learning of semantically relevant frames of sound signals has been overlooked. To this end, we present an end-to-end framework, namely feature pyramid attention network (FPAM), focusing on abstracting the semantically relevant features for ESC. We first extract the feature maps of the preprocessed spectrogram of the sound waveform by a backbone network. Then, to build multi-scale hierarchical features of sound spectrograms, we construct a feature pyramid representation of the sound spectrograms by aggregating the feature maps from multi-scale layers, where the temporal frames and spatial locations of semantically relevant frames are localized by FPAM. Specifically, the multiple features are first processed by a dimension alignment module. Afterward, the pyramid spatial attention module (PSA) is attached to localize the important frequency regions spatially with a spatial attention module (SAM). Last, the processed feature maps are refined by a pyramid channel attention (PCA) to localize the important temporal frames. To justify the effectiveness of the proposed FPAM, visualization of attention maps on the spectrograms has been presented. The visualization results show that FPAM can focus more on the semantic relevant regions while neglecting the noises. The effectiveness of the proposed methods is validated on two widely used ESC datasets: the ESC-50 and ESC-10 datasets. The experimental results show that the FPAM yields comparable performance to state-of-the-art methods. A substantial performance increase has been achieved by FPAM compared with the baseline methods.
翻译:由于音效信号中存在的空间-时空关系没有结构化,因此环境声音分类(ESC)是一个具有挑战性的问题。最近,许多研究侧重于从神经神经网络中抽象的特征,而忽视了声音信号的语义框架。为此,我们提出了一个端对端框架,即金字塔关注网(FPAM),重点是为ESC抽取语义相关特征。我们首先通过主干网络提取预处理的美国FPAM 声波变声波变光谱的地貌图。然后,建立声频光谱图的多级等级特征,我们通过汇总多尺度层的声谱图,构建一个声音光谱图的地貌金字塔代表。在多尺度层的地貌图中,时间框架和语义框架的空间位置是固定的。具体地说,多个特征首先通过一个维度调整模块处理。之后,金字塔空间关注模块(PSA)将重要频率区域与空间关注模块(SAM)相连接,然后,我们建立声波谱图的多级缩缩缩缩图表。最后,通过将E-M数据显示E-M结果的直观测图显示重要的直观测结果的注意度显示重要的时间框架。