• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.5
• /
• pp.543-548
• /
• 2014

Multiple-model based speech recognition framework (MMSR) has been known to be very successful in speech recognition. Since it uses multiple hidden Markov modes (HMMs) that corresponds to various noise types and signal-to-noise ratio (SNR) values, the selected acoustic model can have a close match with the test noisy speech. However, since the number of HMM sets is limited in practical use, the acoustic mismatch still remains as a problem. In this study, we experimentally determined the optimal SNR mapping between the test noisy speech and the HMM set to mitigate the mismatch between them. Improved performance was obtained by employing the SNR mapping instead of using the estimated SNR from the test noisy speech. When we applied the proposed method to the MMSR, the experimental results on the Aurora 2 database show that the relative word error rate reduction of 6.3% and 9.4% was achieved compared to a conventional MMSR and multi-condition training (MTR), respectively.

• Journal of the Korean Regional Science Association
• /
• v.36 no.2
• /
• pp.3-12
• /
• 2020

Recently, metropolitanization and suburbization have been occurring mainly in large cities, and spatial miss-match between residential and employment areas has increased. Spatial miss-match is different in the metropolitan cities and other metropolitan cities in Korea. Seoul and other metropolitan cities have grown to become centers of business functions, while other metropolitan cities have been transformed into residential function centers. Accordingly, The reverse commuting phenomenon is occurring in the rural metropolitan. The reverse commuting phenomenon limits the employment opportunities of specific classes among urban residents, and cause various problems such as environmental pollution and traffic congestion. Therefore, many studies on spatial mismatch and reverse commuting have been conducted, but a number of studies have been conducted on the Seoul metropolitan area, and research on other metropolitan areas is insufficient. The purpose of this study is to analyze the cause of the commuting phenomenon in the metropolitan area of the non-metropolitan area by considering spatial mismatch and understanding the reverse commutation situation in the local metropolitan area. This study is analyzed by a multi-level model and suggests the need for management of industrial location and expansion of residence in suburban.

• Journal of Environmental Science International
• /
• v.29 no.1
• /
• pp.15-23
• /
• 2020

The determination of soil characteristics is important in the simulation of rainfall runoff using a distributed FLO-2D model in catchment analysis. Digital maps acquired using remote sensing techniques have been widely used in modern hydrology. However, the determination of a representative parameter with spatial scaling mismatch is difficult. In this investigation, the FLO-2D rainfall-runoff model is utilized in the Yongdam catchment to test sensitivity based on three different methods (mosaic, arithmetic, and predominant) that describe soil surface characteristics in real systems. The results show that the mosaic method is costly, but provides a reasonably realistic description and exhibits superior performance compared to other methods in terms of both the amount and time to peak flow.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.3
• /
• pp.613-620
• /
• 2010

Additive noise and channel distortion strongly degrade the performance of speaker verification systems, as it introduces distortion of the features of speech. This distortion causes a mismatch between the training and recognition conditions such that acoustic models trained with clean speech do not model noisy and channel distorted speech accurately. This paper presents a phase-related feature extraction method in order to improve the robustness of the speaker verification systems. The instantaneous frequency is computed from the phase of speech signals and features from the histogram of the instantaneous frequency are obtained. Experimental results show that the proposed technique offers significant improvements over the standard techniques in both clean and adverse testing environments.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.39 no.9
• /
• pp.997-1005
• /
• 1990

Integral Error and State Feedback (IESF) controller which incorporates state feedback as a modern control scheme and integral action as a classical control scheme has better performance than that of conventional PID controller in linear time invariant system. But the structure of the IESF controller requires all the state variables of the system and is applicable only to pole assignable linear time invariant systems without time delay. Many industrial processes have large time delay and it is impossible to directly apply IESF control scheme to those processes. In this paper, a new controller structure, Modified Integral Error and State Feedback (MIESF) has been suggested in order to effectively control processes having time delay and its performance has been analyzed and its effectiveness has also been confirmed. As the proposed controller uses output feedback scheme based on integral error and state feedback (IESF) method, it can be simply designed by pole assignment algorithm irrespective of the order of the process. The MIESF controller can follow setpoint changes without overshoot. It is robuster than conventional Smith-Predictor plus PI(D) controller in case of occurring time delay mismatch and extra parameter mismatches between the process and the model. It can enhance control performance by intentional time delay mismatch.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1992.10a
• /
• pp.192-197
• /
• 1992

The position error in multi-axis machine tools are due to many elements, such as the static friction, servo lag, a nonlinear disturbance, the gain mismatch between multi-axis controllers. In the work, modeling for the plant was carried out through the velocity response by the step input signal. Digital PI controllers, LQ optimal controllers and feedforward controllers are designed for a high tracking performance based on the model. The results of experimentation showed that the controllers worked properly.

• Proceedings of the KIEE Conference
• /
• 2002.07c
• /
• pp.1982-1984
• /
• 2002

The admittance of one-port electrostatic actuator are modeled using the steady-state sinusoidal response. Also the admittance of the differential type actuator is derived taking the practical conditions into consideration, although it has no admittance in ideal case. It is a function of biasing error, driving error, and capacitive mismatch including parasitic capacitors. The validity of the admittance model is proved by comparing between the modeled and measured admittances. The distortion in the frequency response curve measured by a capacitive sensor is analyzed and it is concluded that the admittance is the main cause of this distortion.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.236-236
• /
• 2000

Control of Industrial processes is very difficult due to nonlinear dynamics, effect of disturbances and modeling errors. M.Morari proposed Internal Model Control(IMC) system that can be effectively applied to the systems with model uncertainties and time delays. The advantage of IMC systems is their robustness with respect to a model mismatch and disturbances. But it was difficult to apply for nonlinear systems. Adaptive Neuro-Fuzzy Inference System which contains multiple linear models as consequent part is used to model nonlinear systems. Generally, the linear parameters in neuro-fuzzy inference system can be effectively utilized to identify a nonlinear dynamical systems. In this paper, we propose new IMC design method using adaptive neuro-fuzzy inference system for nonlinear plant. Numerical simulation results show that proposed IMC design method has good performance than classical PID controller.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.12
• /
• pp.1090-1095
• /
• 2012

In this paper, we propose a model-based fault diagnosis method applied to vibration data. The fault detection is performed by comparing estimated parameters with normal parameters and deciding if the observed changes can be explained satisfactorily in terms of noise or undermodelling. The key feature of this method is that it accounts for the effects of noise and model mismatch. And we aslo design a classifier for the fault isolation by applying the multiclass SVM (Support Vector Machine) to the estimated parameters. The proposed fault detection and isolation methods are applied to an engine vibration data to show a good performance. The proposed fault detection method is compared with a signal-based fault detection method through a performance analysis.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.47 no.2
• /
• pp.35-42
• /
• 2010

In this study, crosstalk between dominant interconnect pairs in an A/D converter circuit is analyzed in frequency domain and effects of termination conditions on crosstalk are described, based on the practical circuit conditions. An A/D converter circuit is a mixed circuit where both clean and noisy signals coexist such that the circuit probably suffers from distortion by crosstalk. An analog input signal and the reference voltage signal, which dominate the overall conversion performance of the A/D converter circuit, are ready to be distorted by crosstalk and include specific termination conditions, such as non-matching and capacitive termination, respectively. Thus, this study presents the model of crosstalk considering impedance mismatch at both ends and analyzes effects of the practical termination conditions in the analog input and the reference voltage interconnects on crosstalk. A typical circuit configuration of the two interconnects is described and crosstalk including near-end and far-end termination impedances is modeled. Effects of the near-end impedance mismatch in the analog input interconnect and the far-end capacitive termination in the reference voltage interconnect are estimated in the frequency domain by using the model of crosstalk and experiments are performed to confirm the estimated results. Microstrip lines are used as interconnects, involving the increase of loss in high frequencies.