• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.139-142
• /
• 2004

훈련 과정과 인식 과정사이의 주변 잡음과 채널 특성으로 인한 환경의 불일치는 음성 인식 성능을 급격히 저하시킨다. 이러한 차이를 극복하기 위해 다양한 전처리 방법이 제안되어 왔으며, 최근에는 스테레오 데이터와 잡음 음성의 Gaussian Mixture Model(GMM)을 이용하여 보상벡터를 구하는 SPLICE 방법이 좋은 성능을 보여주고 있다. 하지만 차원별로 특징벡터를 보상해주는 추정된 보상벡터는 underestimation되는 경향이 있으며, 그 정도가 각각의 차원마다 달라짐이 관찰되었다. 본 논문에서는 SPLICE 방법에 기반하여 추정된 보상벡터와 실제 보상벡터 사이의 관계를 관찰하여 차원별로 다른 가중치를 적용하는 차원별 가중 보상 방법을 제안하였다. 제안한 방법은 Aurora2 Clean-condition인 경우 baseline 실험 결과에 비해 $68\%$의 높은 상대적인 인식 향상율을 얻었다.

• Journal of Electrical Engineering and Technology
• /
• v.8 no.6
• /
• pp.1389-1399
• /
• 2013

A discrete controller is designed for low power dc-dc switched mode power supplies. The approach is based on time domain and the control loop continuously and concurrently tunes the compensator parameters to meet the converter specifications. A digital state feedback control combined with the load estimator provides a complete compensation, which further improves the dynamic performance of the closed loop system. Simulation of digitally controlled Buck converter is performed with MATLAB/Simulink. Experimental results are given to demonstrate the effectiveness of the controller using LabVIEW with a data acquisition card (model DAQ Pad - 6009).

• Proceedings of the KIEE Conference
• /
• 1989.11a
• /
• pp.450-455
• /
• 1989

In this paper we investigate the application to the motion control of n-link robotic manipulators of recently developed stable factorization approach to tracking and disturbance rejection. Given control scheme consists of an approximate "Computed Torque" based upon a simplified model together with additional state feedback and feedforward compensation, and then, nonlinear control gain has more useful than constant control gain to guarantee robustness to parameter uncertainty and external disturbance. At this stage, we design high gain nonlinear state feedback controller and simulate this controller at the SCARA type robot manipulator of two joint.

• Proceedings of the KIEE Conference
• /
• 2000.07e
• /
• pp.162-166
• /
• 2000

In this paper, a maximum efficiency control technique of real-time processing in which parameter variation is compensated in vector control of an induction motors(I.M.) is proposed. Based on equivalent model of I.M., a loss minimization factor(LMF) with the variations of speed is derived. To solve problem of inaccuracy of LMF curves due to machine parameter variation, rotor resistance estimation is performed by using instantaneous reactive power. The estimated rotor resistance values are applied to the maximum efficiency control with a LMF.

• Journal of Mechanical Science and Technology
• /
• v.16 no.5
• /
• pp.633-638
• /
• 2002

An approach to enhance dimensional accuracy of the grinding process has been presented, and grinding of a glass material with a metal-bonded diamond wheel has been studied. In this study, a grinding tool is suspended flexibly and controlled by an electromagnetic actuator. During grinding, profile error of a ground surface is indirectly measured and fed back to a control system. A model of grinding error has been suggested on which the indirect measurement has been based. An optimal PID control is adopted and effectiveness of the in-process feedback control has been verified experimentally.

• Proceedings of the KSPS conference
• /
• 2003.10a
• /
• pp.37-40
• /
• 2003

This paper presents the preliminary result of the automatic pronunciation scoring for non-native English speakers, and shows the developmental process for an English speech recognizer for the educational and evaluational purposes. The proposed speech recognizer, featuring two refined acoustic model sets, implements the noise-robust data compensation, phonetic alignment, highly reliable rejection, key-word and phrase detection, easy-to-use language modeling toolkit, etc., The developed speech recognizer achieves 0.725 as the average correlation between the human raters and the machine scores, based on the speech database YOUTH for training and K-SEC for test.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10b
• /
• pp.229-234
• /
• 1992

This paper presents a compensator design method for multivariable feedback control systems with saturating actuators based on the concept of the equilibrium point. Am explicit expression for the compensation matrix of the general anti-reset windup(ARW) scheme is derived by minimizing the distances between the equilibrium points. The resulting dynamics of the compensated controller exhibits the reduced model form of the unsaturated system which can be obtained by the singular perturbational method. The proposed method is applicable to any open-loop stable plants with saturating actuators whose controllers are determined by some design technique. An example is given to show the effectiveness of the proposed method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.4
• /
• pp.449-455
• /
• 2011

In this paper, a time-delay problem of a tele-operated control system is investigated and compensated by neural network. The smith predictor requires an exact system model to deal with a time-delay in the system. To compensate for modeling errors in the configuration of the Smith predictor, a neural network approach is presented. Based on forming the Smith predictor structure, the radial basis function(RBF) neural network estimator is used. Simulation and experimental studies are conducted to show the functionality of the proposed method.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.70-70
• /
• 2000

Recently, a neuro-fuzzy approach, a combination of neural networks and fuzzy reasoning, has been playing an important role in the motor control. In this paper, a novel method of fiction compensation using neuro-fuzzy architecture has been shown to significantly improve the performance of a DC motor system with nonlinear friction characteristics. The structure of the controller is the neuro-fuzzy network with the TS(Takagi-Sugeno) model. A back-propagation neural network based on a gradient descent algorithm is employed, and all of its parameters can be on-line trained. The performance of the proposed controller is compared with both a conventional neuro-controller and a PI controller.

• Proceedings of the KSPS conference
• /
• 2006.11a
• /
• pp.7-10
• /
• 2006

본 논문에서는 음성의 모델을 이용하여 확률적인 기반으로 잡음의 마스킹 정도를 측정하는 방법에 대해서 제시한다. 잡음의 마스킹 정도를 측정하는 기준으로서 '잡음 마스킹 확률'을 구하는 방법에 대해서 설명하고 이의 특성에 대해서 알아본다. 그리고 잡음에 대한 '잡음 마스킹 확률'을 이용하여 잡음 환경에서의 음성인식 특징벡터의 성능 향상에 대해 적용해 보았다. 제안된 방법은 ETSI 에서 음성인식 표준실험으로 제시한 Aurora2 데이터베이스 상에서 실험해 보았다. 그 결과 기존의 알고리즘에 비해 16.58%의 성능 향상을 이루어 낼 수 있었다.