期刊
MULTIMEDIA TOOLS AND APPLICATIONS
卷 78, 期 3, 页码 3705-3722出版社
SPRINGER
DOI: 10.1007/s11042-017-5539-3
关键词
Multi-task learning; Convolutional neural networks; Deep residual networks; Audio classification
类别
资金
- National Natural Science Foundation of China [61402306, 61432012]
Audio classification is regarded as a great challenge in pattern recognition. Although audio classification tasks are always treated as independent tasks, tasks are essentially related to each other such as speakers' accent and speakers' identification. In this paper, we propose a Deep Neural Network (DNN)-based multi-task model that exploits such relationships and deals with multiple audio classification tasks simultaneously. We term our model as the gated Residual Networks (GResNets) model since it integrates Deep Residual Networks (ResNets) with a gate mechanism, which extract better representations between tasks compared with Convolutional Neural Networks (CNNs). Specifically, two multiplied convolutional layers are used to replace two feed-forward convolution layers in the ResNets. We tested our model on multiple audio classification tasks and found that our multi-task model achieves higher accuracy than task-specific models which train the models separately.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据