Spectrogram based multi-task audio classification

Zeng, Yuni, Mao, Hua, Peng, Dezhong and Yi, Zhang (2019) Spectrogram based multi-task audio classification. Multimedia Tools and Applications, 78 (3). pp. 3705-3722. ISSN 1380-7501

[img]
Preview
Text
Zeng et al - Spectrogram based multi-task audio classification AAM.pdf - Accepted Version

Download (2MB) | Preview
Official URL: http://dx.doi.org/10.1007/s11042-017-5539-3

Abstract

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.

Item Type: Article
Uncontrolled Keywords: Multi-task learning, Convolutional neural networks, Deep residual networks, Audio classification
Subjects: G400 Computer Science
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User: Paul Burns
Date Deposited: 12 Jun 2019 16:57
Last Modified: 11 Oct 2019 09:18
URI: http://nrl.northumbria.ac.uk/id/eprint/39657

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics


Policies: NRL Policies | NRL University Deposit Policy | NRL Deposit Licence