• The Journal of the Acoustical Society of Korea
• /
• v.28 no.8
• /
• pp.832-842
• /
• 2009

Automatic speech recognition (ASR) has been successfully applied to many real human computer interaction (HCI) applications; however, its performance tends to be significantly decreased under noisy environments. The invention of audio visual speech recognition (AVSR) using an acoustic signal and lip motion has recently attracted more attention due to its noise-robustness characteristic. In this paper, we describe our novel integration scheme for AVSR based on a late integration approach. Firstly, we introduce the robust reliability measurement for audio and visual modalities using model based information and signal based information. The model based sources measure the confusability of vocabulary while the signal is used to estimate the noise level. Secondly, the output probabilities of audio and visual speech recognizers are normalized respectively before applying the final integration step using normalized output space and estimated weights. We evaluate the performance of our proposed method via Korean isolated word recognition system. The experimental results demonstrate the effectiveness and feasibility of our proposed system compared to the conventional systems.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.2
• /
• pp.44-51
• /
• 2001

This Paper the practical echo signal synthesis model to predict the target strength and signal shape of a submarine for a valuable tool to active sonar engineer. It is based on UTAHID (Underwater TArget by Highlight Distribution) model which is relocated highlight points along to external hull for aspect angle, and synthesized echo signal by modified grouping highlights to internal scatter cloud. Proposed model is analyzed target strength characteristics on various incident pulse length, and synthesis signal signature, target time spreading loss, echo elongation effect and so on. Thus it can be efficiently used in various real systems related to underwater target echo signal synthesis, that is, active sonar, acoustic countermeasure and surveillance system.

• Journal of the korean Society of Automotive Engineers
• /
• v.8 no.3
• /
• pp.28-36
• /
• 1986

This study was investigated the feasibility of AE application on in-process detection of tool fracture and chipping. Carbon steel SM45C workpiece with longitudinal slots was turned interruptedly on a lathe. AE RMS signal at tool fracture was observed and also the tangential force and the feed observed at the time of tool fracture, the levels of tangential force and the feed force at the time of fracture decrease considerably. In chipping, high level AE signal was observed but there were no changes of cutting force. Peak AE RMS squared is proportional to the area of tool fracture and resultant force. Fracture model of tool fracture is proposed as $V_{p}$ = $C_{1}$ $E_{1}$F(.DELTA. A)$_{0.5}$ and peak AE RMS shows strong correlation with the fracture parameter F(.DELTA.A)$^{0.5}$.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.31 no.1
• /
• pp.1-10
• /
• 2011

Nonlinear harmonic waves generated at cracked interfaces are investigated both experimentally and theoretically. A compact tension specimen is fabricated and the amplitude of transmitted wave is analyzed as a function of position along the fatigued crack surface. In order to measure as many nonlinear harmonic components as possible a broadband Lithium Niobate ($LiNbO_3$) transducers are employed together with a calibration technique for making absolute amplitude measurements with fluid-coupled receiving transducers. Cracked interfaces are shown to generate high acoustic nonlinearities which are manifested as harmonies in the power spectrum of the received signal. The first subharmonic (f/2) and the second harmonic (2f) waves are found to be dominant nonlinear components for an incident toneburst signal of frequency f. To explain the observed nonlinear behavior a partially closed crack is modeled by planar half interfaces that can account for crack parameters such as crack opening displacement and crack surface conditions. The simulation results show reasonable agreements with the experimental results.

• Journal of the Institute of Convergence Signal Processing
• /
• v.18 no.2
• /
• pp.37-42
• /
• 2017

In this paper, we study on symbol error rate(SER) performance of frequency domain decision feedback equalization for modelled underwater channel. Underwater channel is generated by Bellhop model. Simulation results show that proposed method is efficient for underwater acoustic communication.

• Composites Research
• /
• v.35 no.2
• /
• pp.61-68
• /
• 2022

Composite materials have been used in aerospace industry and many applications because of many advantages such as specific strength and stiffness and corrosion resistance etc. However, it is vulnerable to impacts, these impact lead to formation of cracks in composite laminate and failure of structures. In this paper, we analyzed Mode I fracture toughness of Carbon/Epoxy laminates using acoustic emission signal. DCB test was carried out to analyze Mode I failure characterization of Carbon/Epoxy laminates, and AE sensor was attached to measure AE signal induced by failure of specimen. Fracture toughness was calculated using cumulative AE energy and measured crack length using camera. The calculated fracture toughness was applied in FE model and the result of FE analysis compared with DCB test results. The results show good agreement with between FEM and DCB test results.

• Ocean and Polar Research
• /
• v.34 no.1
• /
• pp.85-91
• /
• 2012

Physical properties such as sound speed contrast (h) and density contrast (g) of the interested target are key parameters to understand acoustic characteristics by using theoretical scattering models. The density and sound speed of moon jellyfish (common jellyfish, Aurelia aurita s.l.) were measured. Sound speed contrast (h) was measured from travel time difference (time-of-flight method) of an acoustic signal in a water tank for APOP studies (Acoustic Properties Of zooplankton). Density contrast (g) was measured by the displacement volume and wet weight (dual-density method). The sound speed remained almost constant as the moon jellyfish increased in bell length. The mean values${\pm}$standard deviation of h and g were $1.0005{\pm}0.0012$ and $0.9808{\pm}0.0195$), respectively. These results will provide important input for use in theoretical scattering models for estimating the acoustic target strength of jellyfish.

• Journal of Ocean Engineering and Technology
• /
• v.11 no.3
• /
• pp.163-169
• /
• 1997

The simulation of target-scattered echo with the moving sonar platform and target in 3-dimensional ocean environment is essential to validate and evaluate the performance of a sonar system. This paper presents the improved target signal simulation on the basis of the highlight(HL) model and its realtime algorithm. In order to simulate the scattering highlight, the highlight is represented as a directional scatterer. The realtime generation algorithm of the target signal is realized by use of DSP chip, TMS320C40, where the 40 channels are equally separated to form a parallel processing task in 4 processors. The presented realtime-version of target signal simulation can be used as a target signal simulator in the development of ACM(Acoustic Counter Measure) and advanced sonar signal processing techniques.

• Journal of Biomedical Engineering Research
• /
• v.23 no.3
• /
• pp.227-233
• /
• 2002

The IME(implantable middle ear) system is Promising due to its ability to free from sound feedback and Produce a good sound quality and intelligibility with low distortion even if it is operated with high gain for severe hearing impaired. The differential electromagnetic vibration transducer. which was developed for using in IME system and has two small magnets attached the same Pole facing in the coil. is not influenced by environmental external magnetic field. Besides, it has high vibration efficiency and good frequency response characteristics. In this Paper, using acoustic model of the transducer and ear model of normal Person. the signal transfer characteristics of the IME system are analyzed and investigated From the differences of the characteristics between normal ear and the IME system, it is Possible that design of the IME system that have the signal transfer characteristics similar to normal person's ear.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.233-247
• /
• 2023

Recently, research on detecting objects in hidden spaces beyond the direct line-of-sight of observers has received attention. Most studies use optical equipment that utilizes the directional of light, but sound that has both diffraction and directional is also suitable for non-line-of-sight(NLOS) research. In this paper, we propose a novel method of detecting objects in non-line-of-sight (NLOS) areas using acoustic signals in the audible frequency range. We developed a deep learning model that extracts information from the NLOS area by inputting only acoustic signals and predicts the properties and location of hidden objects. Additionally, for the training and evaluation of the deep learning model, we collected data by varying the signal transmission and reception location for a total of 11 objects. We show that the deep learning model demonstrates outstanding performance in detecting objects in the NLOS area using acoustic signals. We observed that the performance decreases as the distance between the signal collection location and the reflecting wall, and the performance improves through the combination of signals collected from multiple locations. Finally, we propose the optimal conditions for detecting objects in the NLOS area using acoustic signals.