Shallow and deep feature fusion for digital audio tampering detection

Abstract

Digital audio tampering detection can be used to verify the authenticity of digital audio. However, most current methods use standard electronic network frequency (ENF) databases for visual comparison analysis of ENF continuity of digital audio or perform feature extraction for classification by machine learning methods. ENF databases are usually tricky to obtain, visual methods have weak feature representation, and machine learning methods have more information loss in features, resulting in low detection accuracy. This paper proposes a fusion method of shallow and deep features to fully use ENF information by exploiting the complementary nature of features at different levels to more accurately describe the changes in inconsistency produced by tampering operations to raw digital audio. Firstly, the audio signal is band-pass filtered to obtain the ENF component. Then, the discrete Fourier transform (DFT) and Hilbert transform are performed to obtain the phase and instantaneous frequency of the ENF component. Secondly, the mean value of the sequence variation is used as the shallow feature; the feature matrix obtained by framing and reshaping of the ENF sequence is used as the input of the convolutional neural network; the characteristics of the fitted coefficients are obtained by curve fitting. Then, the local details of ENF are obtained from the feature matrix by the convolutional neural network, and the global information of ENF is obtained by fitting coefficient features through deep neural network (DNN). The depth features of ENF are composed of ENF global information and local information together. The shallow and deep features are fused using an attention mechanism to give greater weights to features useful for classification and suppress invalid features. Finally, the tampered audio is detected by downscaling and fitting with a DNN containing two fully connected layers, and classification is performed using a Softmax layer. The method achieves 97.03% accuracy on three classic databases: Carioca 1, Carioca 2, and New Spanish. In addition, we have achieved an accuracy of 88.31% on the newly constructed database GAUDI-DI. Experimental results show that the proposed method is superior to the state-of-the-art method.

A Unified Interpretable Intelligent Learning Diagnosis Framework for Learning Performance Prediction in Intelligent Tutoring Systems

“…and have been widely used in computer vision [28,29], speech processing [30,31], natural language understanding [32], and other felds [33].…”

Non-Facial Video Spatiotemporal Forensic Analysis Using Deep Learning Techniques

“…Wang et al [27] offered discrete wavelet packet deconstruction and singular point analysis of speech data, to identify audio tampering of time-domain such as audio recognition, addition, replacement, and slicing. It provides a technique for measuring reverberation length for identifying indicators of tampering in audio tapes.…”

DKT-STDRL: Spatial and Temporal Representation Learning Enhanced Deep Knowledge Tracing for Learning Performance Prediction

“…The second stage of KT is from 2015 to the present. Inspired by the great success of deep learning in the field of speech processing [22][23][24][25][26][27][28][29][30] and computer vision [31][32][33][34][35][36][37][38][39], deep learning was introduced into KT. In 2015, deep knowledge tracing (DKT) [13] was proposed, marking the beginning of an era in which DL technologies drove the evolution of KT.…”