arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1811.04448cs.SDeess.AS
收藏

多模态深度神经网络在鸟鸣声识别中的应用

A Multi-modal Deep Neural Network approach to Bird-song identification

Vienna University of Technology(维也纳工业大学);Austrian Institute of Technology(奥地利技术研究所)

Botond Fazeka, Alexander Schindler, Thomas Lidy, Andreas Rauber

摘要:

提出了一种多模态深度神经网络(DNN)方法用于鸟鸣声识别。所提出的方法将音频样本和元数据两者作为输入。音频被馈送到使用四个卷积层的卷积神经网络(CNN)中。另外提供的元数据使用完全连接的层来处理。扁平化的卷积层和元数据的全连接层被连接并馈送到全连接层中。由此产生的架构实现了2. 3.和4.在各种培训配置中在BirdCLEF 2017任务中排名。

英文摘要:

We present a multi-modal Deep Neural Network (DNN) approach for bird song identification. The presented approach takes both audio samples and metadata as input. The audio is fed into a Convolutional Neural Network (CNN) using four convolutional layers. The additionally provided metadata is processed using fully connected layers. The flattened convolutional layers and the fully connected layer of the metadata are joined and fed into a fully connected layer. The resulting architecture achieved 2., 3. and 4. rank in the BirdCLEF2017 task in various training configurations.

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。

↑