基于神经网络的环境声音分类方法研究
Research on Environmental Sound Classification Method Based on Neural Network
徐圣林1
作者信息
- 1. 中国药科大学,江苏 南京 211198
- 折叠
摘要
研究一种基于卷积神经网络(Convolutional Neural Network,CNN)和门控循环单元(Gated Recurrent Unit,GRU)相结合的环境声音分类方法.首先,分析CNN-GRU模型的基本结构;其次,探讨模型进行环境声音分类的数学原理;最后,采用ESC-50 数据集在MATLAB平台上对所提方法进行测试.实验结果表明,CNN-GRU模型的准确率、精确率、召回率及F1 值分别达到了 0.92、0.91、0.89 及 0.90,验证了该模型在处理环境声音分类任务中的有效性和健壮性.
Abstract
A methodology of environmental sound systematization based on the Convolutional Neural Network(CNN)and Gated Recurrent Unit(GRU)is studied.Firstly,the basic structure of the CNN-GRU model is analyzed;secondly,the mathematical principle of the model for environmental sound classification is discussed;finally,the proposed method is tested on the MATLAB platform using the ESC-50 dataset.The experimental results show that the accuracy rate,precision rate,recall rate and F1 value of CNN-GRU model reach 0.92,0.91,0.89 and 0.90,respectively,which verifies the effectiveness and robustness of the model in processing environmental sound classification tasks.
关键词
卷积神经网络(CNN)/门控循环单元(GRU)/声音分类Key words
Convolutional Neural Network(CNN)/Gated Recurrent Unit(GRU)/sound classification引用本文复制引用
出版年
2024
NETL
NSTL
万方数据