Abstract—In this paper, we present a novel approach to the task of automatic adult video detection based on feature porno-sounds recognition using multiple feature vectors and an ensemble of binary classifiers. In this framework, firstly the audio track is extracted and segmented into equal segments from an unknown video. Then each segment is split into sequences of voiced and unvoiced unequal fragments. Multiple feature vectors are extracted for each voiced fragments. Components classifiers including Support Vector Machine (SVM) are trained based on such feature vectors. At the classification, the outputs provided by the component classifiers are combined through fusion rules to form a final output of the ensemble. According to the classification results of these fragments, each segment is classified as erotic or natural. Finally, based on these segments results, the audio track or further the unknown video is labeled “erotic” or “natural”. Online and off-line experiments show that the proposed approach yields high performance than using single classifiers.

Index Terms—Ensemble classifiers, SVM, artificial neural network (ANN), erotic audio, voiced segment.

Ziqiang Shi, Jiqing Han, Tieran Zheng are with the School of Computer Science and Technology, Harbin Institute of Technology, No. 92, West Da-Zhi Street, Harbin, Heilongjiang, China (Tel: +86-451-86417981, e-mail: zqshi, jqha@hit.edu.cn n, zhengtieran@hit.edu.cn).
Boyang Gao is with the Department of Mathematics and Computer Science Ecole Centrale de Lyon, Lyon, France (e-mail: gaoboyang@gmail.com).

Cite: Ziqiang Shi, Tieran Zheng, Jiqing Han, and Boyang Gao, "Erotic Audio Recognition Using Heterogeneous Ensemble Classifiers," International Journal of Computer and Electrical Engineering vol. 4, no. 5, pp. 666-669 , 2012.