Digital Audio Forensics: Microphone and Environment Classification Using Deep Learning

Qamhan, Mustafa A.; Altaheri, Hamdi; Meftah, Ali H.; Muhammad, Ghulam; Alotaibi, Yousef Ajami

doi:10.1109/access.2021.3073786

Cited by 35 publications

(23 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we will introduce the data set, experimental setup, and experimental results. In order to verify the validity of our work, we designed five groups of experiments to verify our contribution : (1) the comparison between the proposed method and machine learning method, (2) the fitting coefficient feature verification, (3) the feature matrix verification, (4) the deep feature verification, and (5) the attention mechanism verification.…”

Section: Resultsmentioning

confidence: 99%

“…More and more softwares for digital audio editing have been developed in recent years, and it has become much easier to edit, tamper and forge digtal audio. However, some edited digital audio may be used in wrong ways, especially in essential security applications such as courts, politics, or business, which may cause serious consequences [1]. For digital audio that is deliberately or even maliciously tampered with, it is essential to develop efficient digital audio tampering detection methods.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Shallow and Deep Feature Fusion for Digital Audio Tampering Detection

Zeng¹,

Yang²,

Wang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Digital Audio tampering detection can be applied to verify the authenticity of digital audio. However, the current methods are mostly based on visual comparison analysis of the continuity of electronic network frequency (ENF) of digital audio with a standard ENF database. It is usually tricky to obtain the ENF database, and the feature expression of the visualization method is weak, which leads to low detection accuracy. In order to solve this problem, this paper proposed an audio tampering detection method based on the fusion of shallow and deep features. Firstly, the band-pass filtering process is performed on the audio signal to obtain the ENF components, and then the discrete Fourier transform and Hilbert transform are applied to obtain the phase and instantaneous frequency of the ENF components. Secondly, the shallow features are extracted by performing framing and fitting operations on the estimated phase and instantaneous frequency. Then, the designed convolutional neural network is used to obtain deep features, and the attention mechanism is applied to fuse shallow features and deep features. Finally, after dimensionality reduction through the fully connected layer, the Softmax layer is used for classification to detect the tampering audio. The method achieves 97.03% accuracy on three classic databases, which are 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.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Shallow and Deep Feature Fusion for Digital Audio Tampering Detection

Zeng¹,

Yang²,

Wang³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In addition to this, the recent literature has considered smartphone identification using distinct sensors, e.g., microphone [ 59 , 60 ], loudspeaker [ 61 , 62 , 63 ], gyroscope [ 64 ], battery consumption [ 65 ], accelerometers [ 66 , 67 ], etc.…”

Section: Related Workmentioning

confidence: 99%

Smartphone Camera Identification from Low-Mid Frequency DCT Coefficients of Dark Images

Berdich

Groza

2022

Entropy

View full text Add to dashboard Cite

Camera sensor identification can have numerous forensics and authentication applications. In this work, we follow an identification methodology for smartphone camera sensors using properties of the Dark Signal Nonuniformity (DSNU) in the collected images. This requires taking dark pictures, which the users can easily do by keeping the phone against their palm, and has already been proposed by various works. From such pictures, we extract low and mid frequency AC coefficients from the DCT (Discrete Cosine Transform) and classify the data with the help of machine learning techniques. Traditional algorithms such as KNN (K-Nearest Neighbor) give reasonable results in the classification, but we obtain the best results with a wide neural network, which, despite its simplicity, surpassed even a more complex network architecture that we tried. Our analysis showed that the blue channel provided the best separation, which is in contrast to previous works that have recommended the green channel for its higher encoding power.

show abstract

“…Deep learning techniques have been shown to be feasible, and the authors propose a new evolutionary neural network architecture for authentication. In Qamhan et al proposed a sound source identification system [10], including the identification of recording device and recording environment. They employed a long-short-term memory (LSTM) hybrid convolutional neural network (CNN) to automatically extract environmental and microphone features from speech.…”

Section: Introductionsmentioning

confidence: 99%

Audio source identification based on residual network

zhang

Luo²

2022

Second International Symposium on Computer Technology and Information Science (ISCTIS 2022)

View full text Add to dashboard Cite

Large number of audio recordings are used in law enforcement and litigation procedures, and it also brings security issues such as the identification of the audio source. This paper mainly studies the problem of source identification (device detection). We proposed an audio source identification framework based on an improved residual network model that introduces a character category output, which will help to improve the identification accuracy for the special case of crossspeaker. Experiments show that this audio source identification framework based on residual network has achieved good results under the condition of non-target recognition task, with the highest accuracy rate reaching above 98%, which outperforms the current audio source identification algorithm.

show abstract

Digital Audio Forensics: Microphone and Environment Classification Using Deep Learning

Cited by 35 publications

References 47 publications

Shallow and Deep Feature Fusion for Digital Audio Tampering Detection

Shallow and Deep Feature Fusion for Digital Audio Tampering Detection

Smartphone Camera Identification from Low-Mid Frequency DCT Coefficients of Dark Images

Audio source identification based on residual network

Contact Info

Product

Resources

About