General audio tagging with ensembling convolutional neural network and statistical features

October 30, 2018 · Entered Twilight · 🏛 Journal of the Acoustical Society of America

"Last commit was 7.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, README.md, config.py, core.py, data_loader.py, data_transform.py, make_predictions.py, networks, pretrainedmodels, stacking_level2.py, train_on_logmel.py, train_on_wave.py, util.py, wavelist.csv

Authors Kele Xu, Boqing Zhu, Qiuqiang Kong, Haibo Mi, Bo Ding, Dezhi Wang, Huaimin Wang arXiv ID 1810.12832 Category cs.CV: Computer Vision Citations 34 Venue Journal of the Acoustical Society of America Repository https://github.com/Cocoxili/DCASE2018Task2/ ⭐ 78 Last Checked 1 month ago

Abstract

Audio tagging aims to infer descriptive labels from audio clips. Audio tagging is challenging due to the limited size of data and noisy labels. In this paper, we describe our solution for the DCASE 2018 Task 2 general audio tagging challenge. The contributions of our solution include: We investigated a variety of convolutional neural network architectures to solve the audio tagging task. Statistical features are applied to capture statistical patterns of audio features to improve the classification performance. Ensemble learning is applied to ensemble the outputs from the deep classifiers to utilize complementary information. a sample re-weight strategy is employed for ensemble training to address the noisy label problem. Our system achieves a mean average precision (mAP@3) of 0.958, outperforming the baseline system of 0.704. Our system ranked the 1st and 4th out of 558 submissions in the public and private leaderboard of DCASE 2018 Task 2 challenge. Our codes are available at https://github.com/Cocoxili/DCASE2018Task2/.