Digital multimedia audio forensics: past, present and future

Zakariah, Mohammed; Khan, Muhammad Khurram; Malik, Hafiz

doi:10.1007/s11042-016-4277-2

Cited by 63 publications

(37 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The monophonic signal X [n] is the input to the MFCC block, and its output is the matrix M (12 × Y). Here, the number of rows of M is the number of Cepstral coefficients configured in the MFCC block (which is set to 12), and the number of columns (Y) depends on the length of the input signal, according to the following Equation:…”

Section: Step 2 Mfccmentioning

confidence: 99%

“…In the case of authentication and integrity verification applications, the aim is to ensure that the information (e.g., digital evidence) was not inadvertently or deliberately altered prior to examination, i.e., what is being demonstrated is that the content has not changed [9,12]. On the other hand, the identification of multimedia contents can be useful when there is only partial access to the information; this is the case of song identification systems (from a few seconds), or also of digital forensic systems, when the data have suffered fragmentation or partial destruction [13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robust Speech Hashing for Digital Audio Forensics

2019

View full text Add to dashboard Cite

The verification of the integrity and authenticity of multimedia content is an essential task in the forensic field, in order to make digital evidence admissible. The main objective is to establish whether the multimedia content has been manipulated with significant changes to its content, such as the removal of noise (e.g., a gunshot) that could clarify the facts of a crime. In this project we propose a method to generate a summary value for audio recordings, known as hash. Our method is robust, which means that if the audio has been modified slightly (without changing its significant content) with perceptual manipulations such as MPEG-4 AAC, the hash value of the new audio is very similar to that of the original audio; on the contrary, if the audio is altered and its content changes, for example with a low pass filter, the new hash value moves away from the original value. The method starts with the application of MFCC (Mel-frequency cepstrum coefficients) and the reduction of dimensions through the analysis of main components (principal component analysis, PCA). The reduced data is encrypted using as inputs two values from a particular binarization system using Collatz conjecture as the basis. Finally, a robust 96-bit code is obtained, which varies little when perceptual modifications are made to the signal such as compression or amplitude modification. According to experimental tests, the BER (bit error rate) between the hash value of the original audio recording and the manipulated audio recording is low for perceptual manipulations, i.e., 0% for FLAC and re-quantization, 1% in average for volume (−6 dB gain), less than 5% in average for MPEG-4 and resampling (using the FIR anti-aliasing filter); but more than 25% for non-perceptual manipulations such as low pass filtering (3 kHz, fifth order), additive noise, cutting and copy-move.

show abstract

Section: Step 2 Mfccmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Robust Speech Hashing for Digital Audio Forensics

2019

View full text Add to dashboard Cite

show abstract

“…Forensics refers to the science that uses scientific methods or expertise to investigate crimes or examine an evidence which may be presented in a court of law. Digital media forensics is a branch of forensic science that involves ensuring that the digital content is accurate and authentic [1]. It focuses on analyzing the evidence to identify any manipulations and counterfeiting, and proving the integrity and authenticity of the digital information, as well as its sources.…”

Section: Introductionmentioning

confidence: 99%

“…Many techniques have been proposed to extract these features and utilize them for microphone and environment classification. A broad categorization of different digital audio forensic techniques has been explored in this respect [1].…”

Section: Introductionmentioning

confidence: 99%

Digital Audio Forensics: Microphone and Environment Classification Using Deep Learning

et al. 2021

View full text Add to dashboard Cite

The recording device along with the acoustic environment plays a major role in digital audio forensics. We propose an acoustic source identification system in this paper, which includes identifying both the recording device and the environment in which it was recorded. A hybrid Convolutional Neural Network (CNN) with Long Short-Term Memory (LSTM) is used in this study to automatically extract environments and microphone features from the speech sound. In the experiments, we investigated the effect of using the voiced and unvoiced segments of speech on the accuracy of the environment and microphone classification. We also studied the effect of background noise on microphone classification in 3 different environments, i.e., very quiet, quiet, and noisy. The proposed system utilizes a subset of the KSU-DB corpus containing 3 environments, 4 classes of recording devices, 136 speakers (68 males and 68 females), and 3600 recordings of words, sentences, and continuous speech. This research combines the advantages of both CNN and RNN (in particular bidirectional LSTM) models, called CRNN. The speech signals were represented as a spectrogram and were fed to the CRNN model as 2D images. The proposed method achieved accuracies of 98% and 98.57% for environment and microphone classification, respectively, using unvoiced speech segments.

show abstract

“…Audio forensics refers to the analysis, acquisition and evaluation of audio recordings admissible to a court of law as forensic evidence. It is typically used to verify the authenticity and integrity of audio evidence, enhancement of audio recording improving speech intelligibility and audibility of low-level sounds, and speaker identification (Khan et al, 2018;Zakariah et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Applying PDC for the Recognition of Firearm's Calibre

Ribeiro

Santos

Gross

et al. 2019

Anais Do 14º Simpósio Brasileiro De Automação Inteligente

View full text Add to dashboard Cite

Nowadays, there has been an enormous increase in audio recordings, some of these of the interest of audio forensics. Audio forensics has been used in many different ways for recognising firearm's calibres. In this work, we use Partial Directed Coherence (PDC) on recordings of capsules hitting the ground to recognise the firearm's calibre. Six different calibres were recorded in a controlled environment, and these audios were cut to have the same size. These audios were analysed using PDC. The results show that the audios of the calibres are orthogonal; thus, for this experiment being impossible to get a false positive while using the proposed methodology.

show abstract

Digital multimedia audio forensics: past, present and future

Cited by 63 publications

References 54 publications

Robust Speech Hashing for Digital Audio Forensics

Robust Speech Hashing for Digital Audio Forensics

Digital Audio Forensics: Microphone and Environment Classification Using Deep Learning

Applying PDC for the Recognition of Firearm's Calibre

Contact Info

Product

Resources

About