General audio tagging with ensembling convolutional neural networks and statistical features

Audio tagging aims to infer descriptive labels from audio clips and it is challenging due to the limited size of data and noisy labels. The solution to the tagging task is described in this paper. The main contributions include the following: an ensemble learning framework is applied to ensemble sta...

Full description

Saved in:
Bibliographic Details
Published inThe Journal of the Acoustical Society of America Vol. 145; no. 6; pp. EL521 - EL527
Main Authors Xu, Kele, Zhu, Boqing, Kong, Qiuqiang, Mi, Haibo, Ding, Bo, Wang, Dezhi, Wang, Huaimin
Format Journal Article
LanguageEnglish
Published United States 01.06.2019
Online AccessGet full text

Cover

More Information
Summary:Audio tagging aims to infer descriptive labels from audio clips and it is challenging due to the limited size of data and noisy labels. The solution to the tagging task is described in this paper. The main contributions include the following: an ensemble learning framework is applied to ensemble statistical features and the outputs from the deep classifiers, with the goal to utilize complementary information. Moreover, a sample re-weight strategy is employed to address the noisy label problem within the framework. The approach achieves a mean average precision of 0.958, outperforming the baseline system with a large margin.
ISSN:0001-4966
1520-8524
DOI:10.1121/1.5111059