基于多状态跳转模型的场景独立音频事件检测方法

Scene-independent sound event detection based on multi-state transition model

针对不同类型事件设计多状态跳转模型,结合两种深度神经网络实现对传统音频事件检测框架的改进。实验表明,在DCASE2017任务2的开发集数据上,改进后的DNN-HMM系统相比于基线系统取得F值8.9%的相对提升和错误率19%的绝对下降;基于多状态跳转模型聚类的卷积神经网络模型(SC-CNN),相比于基线系统取得F值18%的相对提升和错误率30%的绝对下降。

We designed the multi-state transition model for different types of sound events,and combined two kinds of deep neural network to achieve the improvement of the traditional framework.The performance evaluated on the DCASE2017 task2 development dataset showed that the improved DNN-HMM system outperformed the baseline and achieved 19%absolutely lower error rate(ER)and 8.9%relatively higher F-score.The state clustering convolutional neural network(SC-CNN)system based on multi-state transition model also achieved 18%relatively higher F-score and 30%absolutely lower ER,which has reached the international advanced level.