• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.633-638
• /
• 2003

In this paper, we propose a humanoid active audition system which detects the direction of sound and performs speech recognition using just three microphones. Compared with previous researches, this system which has simpler algorithm, fewer microphones and better amplifier shows better performance. In order to verify our system's performance, we install the proposed active audition system to the home service robot, called Hombot II, which has been developed at the KIST (Korea Institute of Science and Technology), thus we confirm excellent performance by experimental results

• Journal of Ocean Engineering and Technology
• /
• v.34 no.3
• /
• pp.227-236
• /
• 2020

Underwater acoustics, which is the domain that addresses phenomena related to the generation, propagation, and reception of sound waves in water, has been applied mainly in the research on the use of sound navigation and ranging (SONAR) systems for underwater communication, target detection, investigation of marine resources and environment mapping, and measurement and analysis of sound sources in water. The main objective of remote sensing based on underwater acoustics is to indirectly acquire information on underwater targets of interest using acoustic data. Meanwhile, highly advanced data-driven machine-learning techniques are being used in various ways in the processes of acquiring information from acoustic data. The related theoretical background is introduced in the first part of this paper (Yang et al., 2020). This paper reviews machine-learning applications in passive SONAR signal-processing tasks including target detection/identification and localization.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.26 no.2
• /
• pp.91-96
• /
• 2014

An acoustical model for detecting the leak location in a buried gas pipeline has been developed. This model is divided into an experimental model for sound diagnosis, and a theoretical model for sound prediction, which is based on the transfer matrix method, representing the sound pressure and the volume velocity as state variables. The power spectrum is measured by attaching only one microphone to the closed end pipe. It has been shown that the response magnitude of acoustic pressure signals calculated by the acoustical model depends upon the thickness and diameter of a pinhole. The validity for the acoustical model has been verified through a comparison between the measured and calculated results.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.4
• /
• pp.12-20
• /
• 1995

This paper describes principles and experimental results in conjunction with examining the possibility of the detection of effects from a cylindrical objects. Cylindrical objects have its own resonance frequency. The frequency varies according to the diameter, length etc. And acoustic sound, whose frequency and the harmonic components corresponding to resonance frequency, is radiated from the object. When an object have defect in itself, the radiated acoustic sound is different from normal one. So we can detect its defect by analysing frequency components of acoustic sound. We proved that detection of defective objects by acoustic signal analysis is possible automatically. Also the result can be applied to other kinds of objects.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.2
• /
• pp.389-396
• /
• 2019

In this paper, various architectures of deep neural networks were applied for sound event detection and their performances were compared using a common audio database. The FNN, CNN, RNN and CRNN were implemented using hyper-parameters optimized for the database as well as the architecture of each neural network. Among the implemented deep neural networks, CRNN performed best at all testing conditions and CNN followed CRNN in performance. Although RNN has a merit in tracking the time-correlations in audio signals, it showed poor performance compared with CNN and CRNN.

• The Journal of the Acoustical Society of Korea
• /
• v.2 no.1
• /
• pp.11-19
• /
• 1983

An irregulary formed chamber was designed and constructed to recognize the direct sound radiated from the sound source and the reflected sound from the walls of the chamber. The sound signal used was tone burst in the frequency response characteristics with the signal detection after transient effect. The direct wave, transient phenomena and the primary reflected sound could be asiily distinguished each other by measurements of the arrival time of the time difference. And also noise could be easily distinguished by the same method. The result obtained can be used in industries for automatic measurement of the sound pressure reponse characteristics with respect to frequencies.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1999.05a
• /
• pp.222-228
• /
• 1999

The two-microphone sound-intensity technique has been used for the detection of defects in radially loaded ball bearings. The difference in the sound-intensity levels measured for bearings with no defect and for those with intentionally introduced defects of different sizes in their elements under various operating conditions of loads and speeds is demonstrated. A change in the intensity frequency spectrum because of the defects is observed. The results show that the detectability of an outer-race defect is much better than that of on inner-race or ball defect. It is difficult to detect defects at lower speeds. Sound-pressure measurements were also performed fur comparison, and it is shown that the detectability of defects by sound-intensity measurements is better than that by sound-pressure measurements.

• The Journal of Korea Robotics Society
• /
• v.17 no.3
• /
• pp.273-281
• /
• 2022

In this paper, we propose a robot sound recognition system that detects various sound events. The proposed system is designed to detect various sound events in real-time by using a microphone on a robot. To get real-time performance, we use a VGG11 model which includes several convolutional neural networks with real-time normalization scheme. The VGG11 model is trained on augmented DB through 24 kinds of various environments (12 reverberation times and 2 signal to noise ratios). Additionally, based on random forest algorithm, a decision logic is also designed to generate event signals for robot applications. This logic can be used for specific classes of acoustic events with better performance than just using outputs of network model. With some experimental results, the performance of proposed sound recognition system is shown on real-time device for robots.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.37 no.11
• /
• pp.1089-1095
• /
• 2009

The radiated sound pressure induced by tapping test is obtained by solving the Rayleigh integral equation. For structurally radiated sound, the sound field is directly coupled to the structural motion. Therefore the impact response should be analyzed. In this paper, the delamination model is used to analyze the impact response of delaminated composite laminates. And efficient spring-mass model has been proposed to model hammer shaped impactor. Predicted sound pressure histories are compared with test data. The influence of damage on the sound pressure and impacted force history of laminates were investigated. The results show that both radiated sound pressure and impact force history are strongly influenced by delamination on laminates. As a result, it is shown that the presented sound based tapping method was found to be reliable for detecting the damage in composite laminate.

• 한국전산유체공학회:학술대회논문집
• /
• 2002.10a
• /
• pp.88-94
• /
• 2002

Curved intakes are commonly used from commercial aircraft to military missile. Sound radiation from the intake of air vehicle affects cabin noise, community noise and military detection. In this paper, Sound radiation from curved intake is computed using the high order, high resolution scheme. The generalized characteristic boundary conditions, adaptive nonlinear artificial dissipation model and conformal mapping for high order, high resolution scheme are used. The geometric change of curved intake and the frequency of acoustic source are considered. Two dimensional Euler equations are solved for theses analyses.