Acoustic Pornography Recognition Using Convolutional Neural Networks and Bag of Refinements

TL;DR

This paper introduces a CNN-based model with multiple refinements for detecting pornographic audio, achieving over 97% accuracy on a large dataset, to aid in filtering harmful content online.

Contribution

The paper proposes a novel CNN model for acoustic pornography recognition and introduces a set of refinements that significantly improve detection accuracy.

Findings

Achieved 92.46% accuracy with the base model.

Refinements increased accuracy to 97.19%.

Validated effectiveness on a large dataset of over 224,000 pornographic audios.

Abstract

A large number of pornographic audios publicly available on the Internet seriously threaten the mental and physical health of children, but these audios are rarely detected and filtered. In this paper, we firstly propose a convolutional neural networks (CNN) based model for acoustic pornography recognition. Then, we research a collection of refinements and verify their effectiveness through ablation studies. Finally, we stack all refinements together to verify whether they can further improve the accuracy of the model. Experimental results on our newly-collected large dataset consisting of 224127 pornographic audios and 274206 normal samples demonstrate the effectiveness of our proposed model and these refinements. Specifically, the proposed model achieves an accuracy of 92.46% and the accuracy is further improved to 97.19% when all refinements are combined.