Audio event recognition (AER), a widely concerned problem, is the problem of classifying environmental sounds, that is, predicting the scenes where they are recorded. Google released the Audioset dataset for AER research in 2017, which greatly expands the size of the previous AER datasets. The dataset has 2 million sound clips, divided into 527 categories. Audioset is a weakly- and multi-labeled dataset. Previous approaches to AER focus on the attention model to solve the weakly labeled problem. However, these methods do not consider the association between labels. Recently, Graph Convolutional Neural Network (GCN) has shown a significant advantage in leveraging relationships between labels. This paper considers the correlation between labels using the GCN method. We improve two basic attention models with GCN structure using label correlation information. Relevant experiments are conducted on the Audioset dataset. The result demonstrates that the use of label relationships can improve the essential model performance.