• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.3
• /
• pp.197-205
• /
• 2020

Korean language has the characteristics that the pronunciation of phoneme units such as vowels and consonants are fixed and the pronunciation associated with a notation does not change, so that foreign learners can approach rather easily Korean language. However, when one pronounces words, phrases, or sentences, the pronunciation changes in a manner of a wide variation and complexity at the boundaries of syllables, and the association of notation and pronunciation does not hold any more. Consequently, it is very difficult for foreign learners to study Korean standard pronunciations. Despite these difficulties, it is believed that systematic analysis of pronunciation errors for Korean words is possible according to the advantageous observations that the relationship between Korean notations and pronunciations can be described as a set of firm rules without exceptions unlike other languages including English. In this paper, we propose a visualization framework which shows the differences between standard pronunciations and erratic ones as quantitative measures on the computer screen. Previous researches only show color representation and 3D graphics of speech properties, or an animated view of changing shapes of lips and mouth cavity. Moreover, the features used in the analysis are only point data such as the average of a speech range. In this study, we propose a method which can directly use the time-series data instead of using summary or distorted data. This was realized by using the deep learning-based technique which combines Self-organizing map, variational autoencoder model, and Markov model, and we achieved a superior performance enhancement compared to the method using the point-based data.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.21 no.1
• /
• pp.80-90
• /
• 2001

The aim of this study is to develop the methodology which enables to identify the mechanical properties of element such as stress intensity factor by using the AE parameters. Considering the multivariate and nonlinear properties of AE parameters such as ringdown count, rise time, energy, event duration and peak amplitude from fatigue cracks of machine element the principal component regression(PCR) and artificial neural network(ANN) models for the estimation of stress intensity factor were developed and validated. The AE parameters were found to be very significant to estimate the stress intensity factor. Since the statistical values including correlation coefficients, standard mr of calibration, standard error of prediction and bias were stable, the PCR and ANN models for stress intensity factor were very robust. The performance of ANN model for unknown data of stress intensity factor was better than that of PCR model.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.3
• /
• pp.513-519
• /
• 2019

Typically, contaminated sediments cause clogging of the drain pipe, which increases the residual water pressure in the drain pipe; this study constructed a system for improving drainage efficiency of tunnels by reducing physical and chemical obstructions through ultrasonic energy generated by a PVDF film. The developed hybrid drainage system utilized a PVDF material film fused with an existing drainage tunnel and maintenance system resulting in the ability to initialize the reverse piezoelectric effect, which was evaluated through an on site application. In order to investigate the maintenance performance of the tunnel drainage system, contaminated sediments were simulated in a drainage pipe to test the effect of ultrasonic conditions on drainage efficiency in the laboratory. As a result of applying the developed portable equipment, the ultrasonic energy was generated for about 20 minutes resulting in a reduction of 74.62% of the contaminated sediments and improving drainage efficiency. From the tunnel, acoustic pressure measurements were taken to calculate the response rate while taking into account the laboratory results. In addition, PVDF film was attached to the transverse and longitudinal side of the drainage pipes where contaminated sediments occur most often in the field tunnel. these calculations show contaminant removal was 90% effective.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.1
• /
• pp.46-54
• /
• 2021

In this paper, active noise control was performed to reduce radiated noise in the low frequency band of dishwashers. First, through an analysis of the noise environment of the dishwasher, it was confirmed that the pump noise contributed the most to the radiated noise in the low frequency band, From the result of the noise environment analysis, the reference signal was selected to be the vibration signal of the pump body. The reference signal was obtained by using the accelerometer on the pump body, which can prevent acoustic feedback. The error signal sensor was selected as a microphone located at 1 m in front of the dishwasher and 0.5 m in height. And to design the controller, the error signal and the reference signal were measured at the operational rpms of the dishwasher at 2,500 rpm, 2,600 rpm and 2,800 rpm, and the secondary path transfer function was measured. The designed controller was mounted on Digital Signal Processor (DSP) equipment, and the control performance was verified experimentally. As a result of the measurement at the 3 operational rpms, the 7th multiple component of pump operating frequency decreased by 1.93 dB, 4.43 dB, 5.15 dB per rpm, and the 12th multiple component decreased by 6.67 dB, 2.34 dB, 4.28 dB per rpm. And overall Sound Pressure Level (SPL) decreased by 0.84 dB, 2.58 dB, 1.48 dB by rpm.

• Geomechanics and Engineering
• /
• v.24 no.3
• /
• pp.215-226
• /
• 2021

To study the evolution mechanism of cracks in rocks with multiple defects, rock-like samples with multiple defects, such as strip-shaped through-going cracks and cavity groups, are used, and the crack propagation law and changes in AE (acoustic emission) and strain of cavity groups under different inclination angles are studied. According to the test results, an increase in the cavity group inclination angle can facilitate the initial damage degree of the rock and weaken the crack initiation stress; the initial crack initiation direction is approximately 90°, and the extension angle is approximately 75~90° from the strip-shaped through-going cracks; thus, the relationship between crack development and cavity group initiation strengthens. The specific performance is as follows: when the initiation angle is 30°, the cracks between the cavities in the cavity group develop relatively independently along the parallel direction of the external load; when the angle is 75°, the cracks between the cavities in the cavity group can interpenetrate, and slip can occur along the inclination of the cavity group under the action of the shear mechanism rupture. With the increase in the inclination angle of the cavity group, the AE energy fluctuation frequency at the peak stress increases, and the stress drop is obvious. The larger the cavity group inclination angle is, the more obvious the energy accumulation and the more severe the rock damage; when the cavity group angle is 30° or 75°, the peak strain of the local area below the strip-shaped through-going fracture plane is approximately three times that when the cavity group angle is 45° and 60°, indicating that cracks are easily generated in the local area monitored by the strain gauge at this angle, and the further development of the cracks weakens the strength of the rock, thereby increasing the probability of major engineering quality damage. The research results will have important reference value for hazard prevention in underground engineering projects through rock with natural and artificial defects, including tunnels and air-raid shelters.

• Phonetics and Speech Sciences
• /
• v.14 no.4
• /
• pp.45-56
• /
• 2022

This paper proposes an optimal methodology for automatically diagnosing and predicting the severity of the chronic kidney disease (CKD) using patients' utterances. In patients with CKD, the voice changes due to the weakening of respiratory and laryngeal muscles and vocal fold edema. Previous studies have phonetically analyzed the voices of patients with CKD, but no studies have been conducted to classify the voices of patients. In this paper, the utterances of patients with CKD were classified using the variety of utterance types (sustained vowel, sentence, general sentence), the feature sets [handcrafted features, extended Geneva Minimalistic Acoustic Parameter Set (eGeMAPS), CNN extracted features], and the classifiers (SVM, XGBoost). Total of 1,523 utterances which are 3 hours, 26 minutes, and 25 seconds long, are used. F1-score of 0.93 for automatically diagnosing a disease, 0.89 for a 3-classes problem, and 0.84 for a 5-classes problem were achieved. The highest performance was obtained when the combination of general sentence utterances, handcrafted feature set, and XGBoost was used. The result suggests that a general sentence utterance that can reflect all speakers' speech characteristics and an appropriate feature set extracted from there are adequate for the automatic classification of CKD patients' utterances.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.6
• /
• pp.478-488
• /
• 2023

This paper investigates the naval application of laser communication as a potential replacement for traditional acoustic wave communication in underwater environments. We developed a laser transceiver using Arduino and MATLAB, conducting a water tank experiment to validate communication feasibility across diverse underwater conditions. In the first experiment, when transmitting data through a laser, the desired message was converted into data and transmitted, received, and confirmed to be converted into the correct message. In the second experiment, the operation of communication in underwater situations was confirmed, and in the third experiment, the intensity of light was measured using the CDS illuminance sensor module and the limits of laser communication were measured and confirmed in various underwater situations. Additionally, MATLAB code was employed to gather data on salinity, water temperature, and water depth for calculating turbidity. Optimal wavelength values (532nm, 633nm, 785nm, 1064nm) corresponding to calculated turbidity levels (5, 20, 55, 180) were determined and presented. The study then focuses on analyzing potential applications in naval tactical communication, remote sensing, and underwater drone control. Finally, we propose measures for overcoming current technological limitations and enhancing performance.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.6
• /
• pp.250-258
• /
• 2007

Current speech recognition technology s achieved high performance with the development of hardware devices, however it is insufficient for some applications where high reliability is required, such as voice control of powered wheelchairs for disabled persons. For the system which aims to operate powered wheelchairs safely by voice in real environment, we need to consider that non-voice commands such as user s coughing, breathing, and spark-like mechanical noise should be rejected and the wheelchair system need to recognize the speech commands affected by disability, which contains specific pronunciation speed and frequency. In this paper, we propose non-voice rejection method to perform voice/non-voice classification using both YIN based fundamental frequency(F0) extraction and reliability in preprocessing. We adopted a multi-template dictionary and acoustic modeling based speaker adaptation to cope with the pronunciation variation of inarticulately uttered speech. From the recognition tests conducted with the data collected in real environment, proposed YIN based fundamental extraction showed recall-precision rate of 95.1% better than that of 62% by cepstrum based method. Recognition test by a new system applied with multi-template dictionary and MAP adaptation also showed much higher accuracy of 99.5% than that of 78.6% by baseline system.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.4
• /
• pp.318-327
• /
• 2009

In this paper, we propose a 3-D geometric localization method for near-field broadband source in shallow water environments. According to the waveguide invariant theory, slope of the interference pattern which is seen in a sensor spectrogram directly proportional to a range of the source. The relative ratio of the range between source and sensors was estimated by matching of two interference patterns in spectrogram. Then this ratio is applied to the Apollonius's circle which shows the locus of a source whose range ratio from two sensors is constant. Two Apollonius's circles from three sensors make the intersection point that means the horizontal range and the azimuth angle of the source. And this intersection point is constant with source depth. Therefore the source depth can be estimated using 3-D hyperboloid equation whose range difference from two sensors is constant. To evaluate a performance of the proposed localization algorithm, simulation is performed using acoustic propagation program and analysis of localization error is demonstrated. From simulation results, error estimate for range and depth is described within 50 m and 15 m respectively.

• The Journal of the Acoustical Society of Korea
• /
• v.43 no.2
• /
• pp.214-224
• /
• 2024

Sonobuoys are disposable devices that utilize sound waves for information gathering, detecting engine noises, and capturing various acoustic characteristics. They play a crucial role in accurately detecting underwater targets, making them effective detection systems in anti-submarine warfare. Existing sonobuoy deployment methods in multistatic systems often rely on fixed patterns or heuristic-based rules, lacking efficiency in terms of the number of sonobuoys deployed and operational time due to the unpredictable mobility of the underwater targets. Thus, this paper proposes an optimal sonobuoy placement strategy for Unmanned Aerial Vehicles (UAVs) to overcome the limitations of conventional sonobuoy deployment methods. The proposed approach utilizes reinforcement learning in a simulation-based experimental environment that considers the movements of the underwater targets. The Unity ML-Agents framework is employed, and the Proximal Policy Optimization (PPO) algorithm is utilized for UAV learning in a virtual operational environment with real-time interactions. The reward function is designed to consider the number of sonobuoys deployed and the cost associated with sound sources and receivers, enabling effective learning. The proposed reinforcement learning-based deployment strategy compared to the conventional sonobuoy deployment methods in the same experimental environment demonstrates superior performance in terms of detection success rate, deployed sonobuoy count, and operational time.