arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.06178eess.AScs.LGcs.SD
收藏

DCASE 2019年任务4的引导学习卷积系统

Guided Learning Convolution System for DCASE 2019 Task 4

Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学)

Liwei Lin, Xiangdong Wang, Hong Liu, Yueliang Qian

摘要:

在本文中,我们详细描述了我们提交给DCASE 2019任务4的系统:家庭环境中的声音事件检测(SED)。我们采用一个带有嵌入级注意力池模块的卷积神经网络(CNN)来解决这个问题,通过考虑非平衡数据集中多个事件共现造成的干扰,利用解纠缠特征来提高模型的性能。为了利用未标记的数据,我们采用引导学习进行半监督学习。在模型输出概率的后处理中,采用了一组窗口大小自适应的中值滤波器。我们还分析了合成数据对模型性能的影响,最终在验证集上实现了45.43%的基于事件的F-度量,在测试集上实现了42.7%的基于事件的F-度量。与其他参与者相比,我们提交的挑战系统实现了最佳性能。

英文摘要:

In this paper, we describe in detail the system we submitted to DCASE2019 task 4: sound event detection (SED) in domestic environments. We employ a convolutional neural network (CNN) with an embedding-level attention pooling module to solve it. By considering the interference caused by the co-occurrence of multiple events in the unbalanced dataset, we utilize the disentangled feature to raise the performance of the model. To take advantage of the unlabeled data, we adopt Guided Learning for semi-supervised learning. A group of median filters with adaptive window sizes is utilized in the post-processing of output probabilities of the model. We also analyze the effect of the synthetic data on the performance of the model and finally achieve an event-based F-measure of 45.43% on the validation set and an event-based F-measure of 42.7% on the test set. The system we submitted to the challenge achieves the best performance compared to those of other participates.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑