• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.4
• /
• pp.16-22
• /
• 2012

In this paper, the forensic marking algorithm is proposed using psychoacoustic model II and MDCT for high-quality audio. The proposed forensic marking method, that inserts the user fingerprinting code of the audio content into the selected sub-band, in which audio signal energy is lower than the spectrum masking level. In the range of the one frame which has 2,048 samples for FFT of original audio signal, the audio forensic marking is processed in 3 sub-bands. According to the average attack of the fingerprinting codes, one frame's SNR is measured on 100% trace ratio of the collusion codes. When the lower strength 0.1 of the inserted fingerprinting code, SNR is 38.44dB. And in case, the added strength 0.5 of white gaussian noise, SNR is 19.09dB. As a result, it confirms that the proposed audio forensic marking algorithm is maintained the marking robustness of the fingerprinting code and the audio high-quality.

• Journal of Digital Contents Society
• /
• v.15 no.3
• /
• pp.357-363
• /
• 2014

In this paper, we propose a new audio forensic marking system for protecting the copyright of the Internet-based music streaming services. In the proposed method, in order to guarantee the QoS of the streaming service, high speed, and generates a forensic mark inserted MP3 file. We make pre-marking process and generate a new forensic marked MP3 file, a combination of the pre-marked MP3 frame, the inserted user information. Experimental results show that the proposed method satisfactory results robustness and imperceptibility, and real-time properties. In addition, we were confirmed that the real-time embedding and detection from the streaming-based audio forensic marking system that has been implemented on the server/client is possible.

• Journal of Korea Society of Industrial Information Systems
• /
• v.19 no.2
• /
• pp.73-83
• /
• 2014

Thanks to the development of diverse audio editing Technology, audio file can be easily revised. As a result, diverse social problems like forgery may be caused. Digital forensic technology is actively studied to solve these problems. In this paper, a hand-held device identification method, an area of digital forensic technology is proposed. It uses the noise features of devices caused by the design and the integrated circuit of each device but cannot be identified by the audience. Wiener filter is used to get the noise sounds of devices and their acoustic features are extracted via MIRtoolbox and then they are trained by multi-layer neural network. To evaluate the proposed method, we use 5-fold cross-validation for the recorded data collected from 6 mobile devices. The experiments show the performance 99.9%. We also perform some experiments to observe the noise features of mobile devices are still useful after the data are uploaded to UCC. The experiments show the performance of 99.8% for UCC data.

• Phonetics and Speech Sciences
• /
• v.6 no.2
• /
• pp.21-28
• /
• 2014

We propose a novel scheme for digital audio authentication of given audio files which are edited by inserting small audio segments from different environmental sources. The purpose of this research is to detect inserted sections from given audio files. We expect that the proposed method will assist human investigators by notifying suspected audio section which considered to be recorded or transmitted on different environments. GMM-UBM and GSV-SVM are applied for modeling the dominant environment of a given audio file. Four kinds of likelihood ratio based scores and SVM score are used to measure the likelihood for a dominant environment model. We also use an ensemble score which is a combination of the aforementioned five kinds of scores. In the experimental results, the proposed method shows the lowest average equal error rate when we use the ensemble score. Even when dominant environments were unknown, the proposed method gives a similar accuracy.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.1
• /
• pp.115-127
• /
• 2024

The recent increase in digital audio media has greatly expanded the size and diversity of sound data, which has increased the importance of sound data analysis in the digital forensics process. However, the lack of standardized procedures and guidelines for sound data analysis has caused problems with the consistency and reliability of analysis results. The digital environment includes a wide variety of audio formats and recording conditions, but current audio forensic methodologies do not adequately reflect this diversity. Therefore, this study identifies Life-Cycle-based sound data elemental technologies and provides overall guidelines for sound data analysis so that effective analysis can be performed in all situations. Furthermore, the identified elemental technologies were analyzed for use in the development of digital forensic techniques for sound data. To demonstrate the effectiveness of the life-cycle-based sound data elemental technology identification system presented in this study, a case study on the process of developing an emergency retrieval technology based on sound data is presented. Through this case study, we confirmed that the elemental technologies identified based on the Life-Cycle in the process of developing digital forensic technology for sound data ensure the quality and consistency of data analysis and enable efficient sound data analysis.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.312-318
• /
• 2022

This paper proposes a model which classifies the type of guns and information about sound source location using deep neural network. The proposed classification model is composed of convolutional neural networks (CNN) and long short-term memory (LSTM). For training and test the model, we use the Gunshot Audio Forensic Dataset generated by the project supported by the National Institute of Justice (NIJ). The acoustic signals are transformed to Mel-Spectrogram and they are provided as learning and test data for the proposed model. The model is compared with the control model consisting of convolutional neural networks only. The proposed model shows high accuracy more than 90 %.

• MALSORI
• /
• no.43
• /
• pp.45-55
• /
• 2002

High reliability of automatic speaker recognition regardless of voice conditions is necessary for forensic application. Audio recordings in real cases are not consistent in voice conditions, such as duration, time interval of recording, given text or conversational speech, transmission channel, etc. In this study the variation of verification error rate of ASR system with the voice conditions was investigated. As a result in order to decrease both false rejection rate and false acception rate, the various voices should be used for training and the duration of train voices should be longer than the test voices.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.807-812
• /
• 2022

Recently, as the number of voice recording files submitted as court evidence increases, the number of cases claiming forgery is also increasing. If the audio recording file structure and metadata, which are objective grounds, are completely forged, it is actually impossible to detect forgery of the sophisticated audio recording file. It is extremely rare for the court to reject the file structure and metadata analysis performed with the forged audio recording file. The purpose of this study is to prove that forgery of voice recording file structure and metadata is easily possible. To this end, in this study, it was introduced that forgery detection is impossible when the 'mixed paste' function, which enables sophisticated editing based on the typification of the editing method of voice recording files, is applied. Moreover, it has been proven through experiments that forgery of file structure and metadata is possible. Therefore, a stricter standard for judging the admissibility of evidence is required when the audio recording file is adopted as digital evidence. This study will not only contribute to the standard of integrity in the adoption of digital evidence by judges, but will also contribute to the method of constructing a dataset for artificial intelligence in detecting forgery of recorded files that is expected to be developed in the future.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.12
• /
• pp.2153-2158
• /
• 2016

Multimedia such as image, audio, and video is easy to create and distribute with the advance of IT. Since novice uses them for illegal purposes, multimedia forensics are required to protect contents and block illegal usage. This paper presents a multimedia forensic algorithm for video to identify the device used for acquiring unknown video files. First, the way to calculate a sensor pattern noise using Wiener filter (W-SPN) is presented, which comes from the imperfection of photon detectors against light. Then, the way to identify the device is explained after estimating W-SPNs from the reference device and the unknown video. For the experiment, 30 devices including DSLR, compact camera, smartphone, and camcorder are tested and analyzed quantitatively. Based on the results, the presented algorithm can achieve the 96.0% identification accuracy.

• Phonetics and Speech Sciences
• /
• v.14 no.3
• /
• pp.103-112
• /
• 2022

Due to the popularization of smartphones, most of the recorded speech files submitted as evidence of recent crimes are produced by smartphones, and the integrity (forgery) of the submitted speech files based on smartphones is emerging as a major issue in the investigation and trial process. Samsung smartphones with the highest domestic market share are distributed with built-in speech recording applications that can record calls and voice, and can edit recorded speech. Unlike editing through third-party speech (audio) applications, editing by their own builtin speech applications has a high similarity to the original file in metadata structures and attributes, so more precise analysis techniques need to prove integrity. In this study, we constructed a speech file metadata database for speech files (original files) recorded by 34 Samsung smartphones and edited speech files edited by their built-in speech recording applications. We analyzed by comparing the metadata structures and attributes of the original files to their edited ones. As a result, we found significant metadata differences between the original speech files and the edited ones.