• Convergence Security Journal
• /
• v.24 no.2
• /
• pp.201-207
• /
• 2024

Voice is a critical element of human communication, and the development of speech recognition models is one of the significant achievements in artificial intelligence, which has recently been applied in various aspects of human life. The application of speech recognition models in the military field is also inevitable. However, before artificial intelligence models can be applied in the military, it is necessary to research their vulnerabilities. In this study, we evaluates the military applicability of the multilingual speech recognition model "Whisper" by examining its vulnerabilities to battlefield noise, white noise, and adversarial attacks. In experiments involving battlefield noise, Whisper showed significant performance degradation with an average Character Error Rate (CER) of 72.4%, indicating difficulties in military applications. In experiments with white noise, Whisper was robust to low-intensity noise but showed performance degradation under high-intensity noise. Adversarial attack experiments revealed vulnerabilities at specific epsilon values. Therefore, the Whisper model requires improvements through fine-tuning, adversarial training, and other methods.

• Convergence Security Journal
• /
• v.24 no.2
• /
• pp.161-165
• /
• 2024

Recently, speech recognition models have been advancing, accompanied by the development of various speech processing technologies to obtain high-quality data. In the defense sector, efforts are being made to integrate technologies that effectively remove noise from speech data in noisy battlefield situations and enable efficient speech recognition. This paper proposes a method for effective speech recognition in the midst of diverse noise in a battlefield scenario, allowing commanders to convey orders. The proposed method involves noise removal from noisy speech followed by text conversion using OpenAI's Whisper model. Experimental results show that the proposed method reduces the Character Error Rate (CER) by 6.17% compared to the existing method that does not remove noise. Additionally, potential applications of the proposed method in the defense are discussed.

• 한국전산유체공학회:학술대회논문집
• /
• 2009.04a
• /
• pp.70-74
• /
• 2009

The helicopter development technology is improved by the increasing of computing power and advanced test facilities. The increasing efficiency of fuel consuming by the developing of improved lift-to-drag rotor system is the major issue, the noise reduction for ecology(civil area) and increase of survivability to reduce noise detection(battlefield) also are important. This investigation shows the helicopter external noise flight test methods, conventional military helicopter's(UH-60) experimental results and the numerical modeling method for aero-acoustic of rotor blade and the result of CAA(Computational Aero-Acoustic) for main rotor blade.

• 한국전산유체공학회:학술대회논문집
• /
• 2008.03a
• /
• pp.302-307
• /
• 2008

The development technology for the helicopter is improved by the increasing of computing power and advanced test facilities. The increasing efficiency of fuel consuming by the developing of improved lift-to-drag rotor system is the major issue, the noise reduction for ecology(civil area) and increase of survivability to reduce noise detection(battlefield) also are important. This investigation shows the classification of helicopter external noise and requirements, the noise flight test methods, the numerical modeling method for aero-acoustic of rotor blade and the result of CAA(Computational Aero-Acoustic) for main rotor blade.

• 한국전산유체공학회:학술대회논문집
• /
• 2008.10a
• /
• pp.302-307
• /
• 2008

The development technology for the helicopter is improved by the increasing of computing power and advanced test facilities. The increasing efficiency of fuel consuming by the developing of improved lift-to-drag rotor system is the major issue, the noise reduction for ecology(civil area) and increase of survivability to reduce noise detection(battlefield) also are important. This investigation shows the classification of helicopter external noise and requirements, the noise flight test methods, the numerical modeling method for aero-acoustic of rotor blade and the result of CAA(Computational Aero-Acoustic) for main rotor blade.

• The Journal of the Acoustical Society of Korea
• /
• v.32 no.6
• /
• pp.472-483
• /
• 2013

Actual maritime exercise for improving the capability of submarine sonar operator leads to a lot of cost and constraints. Sonar simulator maximizes the capability of sonar operator and training effect by solving these problems and simulating a realistic battlefield environment. In this study, a passive sonar simulator algorithm is suggested, where the simulator is divided into three modules: maneuvering module, noise source module, and sound propagation module. Maneuvering module is implemented in three-dimensional coordinate system and time interval is set as the rate of vessel changing course. Noise source module consists of target noise, ocean ambient noise, and self noise. Target noise is divided into modulated/unmodulated and narrowband/broadband signals as their frequency characteristics, and they are applied to ship radiated noise level depending on the vessel tonnage and velocity. Ocean ambient noise is simulated depending on the wind noise considering the waveguide effect and other ambient noise. Self noise is also simulated for flow noise and insertion loss of sonar-dome. The sound propagation module is based on ray propagation, where summation of amplitude, phase, and time delay for each eigen-ray is multiplied by target noise in the frequency domain. Finally, simulated results based on various scenarios are in good agreement with generated noise in the real ocean.

• Convergence Security Journal
• /
• v.23 no.3
• /
• pp.73-81
• /
• 2023

The progress in science and technology has widened the scope of the battlefield, leading to the emergence of cyber electronic warfare that exploits electromagnetic waves and networks. Drones have become more important due to advancements in battery technology and navigation systems. Nevertheless, tackling drone threats comes with its own set of difficulties. Radar plays a vital role in detecting drones, offering long-range capabilities and independence from weather conditions. However, the battlefield presents unique challenges like dealing with high levels of signal noise and ensuring the safety of the detection assets. This paper proposes various approaches to improve the operation of drone detection radar in cyber electronic warfare, with a focus on enhancing signal processing techniques, utilizing low probability of interception (LPI) radar, and implementing optimized deployment strategies.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.14 no.3
• /
• pp.423-431
• /
• 2011

Warfighting experimentation is an important process for identifying requirements against changing military environment and for verifying proposed measures for reforming military service. The wargame simulation experiment is regarded as one of the most effective means to warfighting experimentation, and its importance is increasing than ever. On the other hand, the results of wargame experiments could be unreliable due to the uncertainty involved in the experimental procedure. To improve the reliability of the experimental results, systematic experimental procedures and analysis methods must be employed, and the design and analysis of experiments technique can be used effectively for this purpose. In this paper, AWAM, a wargame simulator, is used to optimize the organization of operational troops. The simulation model describes a warfighting situation in which the 'survival rate of our force' and the 'survival rate of the enemy force' are considered as responses, 'the numbers of weapons in the squad' as control factors, and 'the uncontrollable variables of the battlefield' as noise factors. In addition, for the purpose of effective experimentation, the product array approach in which the inner and outer orthogonal arrays are crossed is adopted. Then, the signal-to-noise-ratio for each response and the desirabilities for the means and standard deviations of responses are calculated and used to determine a compromise optimal solution. The experimental procedures and analysis methods developed in this paper can provide guidelines for designing and analyzing wargame simulation experiments for similar warfighting situations.