• 제목/요약/키워드: Model-based Compensation

검색결과 525건 처리시간 0.025초

시변 잡음에 강인한 음성 인식을 위한 PCA 기반의 Variational 모델 생성 기법 (PCA-based Variational Model Composition Method for Roust Speech Recognition with Time-Varying Background Noise)

  • 김우일
    • 한국정보통신학회논문지
    • /
    • 제17권12호
    • /
    • pp.2793-2799
    • /
    • 2013
  • 본 논문에서는 시간에 따라 변하는 잡음 환경에 강인한 음성 인식을 위해 효과적인 특징 보상 기법을 제안한다. 제안하는 기법에서는 기존의 Variational 모델 생성 기법의 모델 정확도를 향상시키고자 PCA를 도입한다. 제안된 기법은 다중 모델을 사용하는 PCGMM 기반의 특징 보상에 적용된다. 실험 결과는 제안한 PCA 기반의 Variational 모델 생성 기법이 배경 음악 환경의 다양한 SNR 조건에서 기존의 전처리 기법에 비하여 음성 인식 성능을 향상 시키는데 우수함을 입증한다. 제안한 모델 생성 기법이 기존의 Variational 모델 생성 방법에 비해 배경 음악 환경에서 평균 12.14%의 상대적 인식 성능 향상률을 나타낸다.

볼테라 필터를 이용한 디지털 통신 채널의 적응 비선형 보상기법 (Adaptive nonlinear compensation of digital communication channels using a volterra filter)

  • 김진영;최봉준;남상원
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
    • /
    • pp.16-19
    • /
    • 1996
  • The objective of this paper is to present a new adaptive nonlinear compensation method, which is based upon the Pth-order inverse theory and can be implemented in a systematic way, for weakly nonlinear systems that can be modeled by a Volterra series. In particular, employment of the proposed approach for the linearization of a given nonlinear system leads to the effective elimination of (up to a required order) nonlinearities in the overall system output. To demonstrate the feasibility of the proposed method, simulation results using a satellite communication system model are also provided.

  • PDF

Analysis, Modeling and Compensation of Dynamic Imbalance Error for a Magnetically Suspended Sensitive Gyroscope

  • Xin, Chaojun;Cai, Yuanwen;Ren, Yuan;Fan, Yahong;Xu, Guofeng;Lei, Xu
    • Journal of Magnetics
    • /
    • 제21권4호
    • /
    • pp.529-536
    • /
    • 2016
  • Magnetically suspended sensitive gyroscopes (MSSGs) provide an interesting alternative for achieving precious attitude angular measurement. To effectively reduce the measurement error caused by dynamic imbalance, this paper proposes a novel compensation method based on analysis and modeling of the error for a MSSG. Firstly, the angular velocity measurement principle of the MSSG is described. Then the analytical model of dynamic imbalance error has been established by solving the complex coefficient differential dynamic equations of the rotor. The generation mechanism and changing regularity of the dynamic imbalance error have been revealed. Next, a compensation method is designed to compensate the dynamic imbalance error and improve the measurement accuracy of the MSSG. The common issues caused by dynamic imbalance can be effectively resolved by the proposed method in gyroscopes with a levitating rotor. Comparative simulation results before and after compensation have verified the effectiveness and superiority of the proposed compensation method.

모델 참조 제어 방법에 의한 새로운 마찰 보상 방법 (New friction compensation method by model reference approach)

  • 마진석;이무영;변승완
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
    • /
    • pp.492-495
    • /
    • 1997
  • Integral type system is that a system is represented by a proper rational function. In this paper, novel control scheme based on model reference approach is proposed for integral type system. The proposed scheme compensates various undesirable effects of the system. In especially, the proposed scheme applied to DC servo control system, analyzed its control characteristic. Performances of the proposed system show excellent control characteristics; complete compensation of the undesirable nonlinear friction and load viscous, For proving realistic validities, LOS(Line Of Sight) stabilization system which has typically many nonlinear effects is experimented. After executing the computer simulation in "MATLAB", then the results are compared with the experiments. The results are very similar in theoretical study and the proposed control scheme is successfully verified. verified.

  • PDF

강인한 음성인식을 위한 SPLICE 기반 잡음 보상의 성능향상 (Performance Improvement of SPLICE-based Noise Compensation for Robust Speech Recognition)

  • 김형순;김두희
    • 음성과학
    • /
    • 제10권3호
    • /
    • pp.263-277
    • /
    • 2003
  • One of major problems in speech recognition is performance degradation due to the mismatch between the training and test environments. Recently, Stereo-based Piecewise LInear Compensation for Environments (SPLICE), which is frame-based bias removal algorithm for cepstral enhancement using stereo training data and noisy speech model as a mixture of Gaussians, was proposed and showed good performance in noisy environments. In this paper, we propose several methods to improve the conventional SPLICE. First we apply Cepstral Mean Subtraction (CMS) as a preprocessor to SPLICE, instead of applying it as a postprocessor. Secondly, to compensate residual distortion after SPLICE processing, two-stage SPLICE is proposed. Thirdly we employ phonetic information for training SPLICE model. According to experiments on the Aurora 2 database, proposed method outperformed the conventional SPLICE and we achieved a 50% decrease in word error rate over the Aurora baseline system.

  • PDF

원거리 음성인식을 위한 MLLR적응기법 적용 (MLLR-Based Environment Adaptation for Distant-Talking Speech Recognition)

  • 권석봉;지미경;김회린;이용주
    • 대한음성학회지:말소리
    • /
    • 제53호
    • /
    • pp.119-127
    • /
    • 2005
  • Speech recognition is one of the user interface technologies in commanding and controlling any terminal such as a TV, PC, cellular phone etc. in a ubiquitous environment. In controlling a terminal, the mismatch between training and testing causes rapid performance degradation. That is, the mismatch decreases not only the performance of the recognition system but also the reliability of that. Therefore, the performance degradation due to the mismatch caused by the change of the environment should be necessarily compensated. Whenever the environment changes, environment adaptation is performed using the user's speech and the background noise of the changed environment and the performance is increased by employing the models appropriately transformed to the changed environment. So far, the research on the environment compensation has been done actively. However, the compensation method for the effect of distant-talking speech has not been developed yet. Thus, in this paper we apply MLLR-based environment adaptation to compensate for the effect of distant-talking speech and the performance is improved.

  • PDF

예약기반 장기수행 변동처리를위한 비용인지 시간계획 (A Cost-aware Scheduling for Reservation-Based Long Running Transactions)

  • 림청;팜폭헝;변정용
    • 한국정보처리학회:학술대회논문집
    • /
    • 한국정보처리학회 2011년도 추계학술발표대회
    • /
    • pp.1248-1251
    • /
    • 2011
  • Web Service technologies make the automation of business activities that are distributed across multiple enterprises possible. Existing extended transaction protocols typically resort to compensation actions to regain atomicity and consistency. A reservation-based transaction protocol is proposed to reduce high compensation risk. However, for a serial long running transaction processing, the resource that is reserved in the early stage may be released due to resource holding time expires. Therefore, our analysis theoretically illustrates a scheduling scheme that tries to prevent the loss of resource holding as well as gain an optimized execution plan with minimum compensation cost. In order to estimate cost of different schedules, we set up a costing model and cost metric to quantize compensation risk.

종업원의 주식보상시스템이 기업성과에 미치는 영향 (The Effect on Firm's Performance of Employee Stock Option)

  • 박종혁
    • 경영과정보연구
    • /
    • 제28권1호
    • /
    • pp.71-97
    • /
    • 2009
  • 주식보상시스템의 도입으로 기업은 최소의 비용으로 유능한 인재를 확보함으로써 기업의 경쟁력을 강화할 수 있고, 특히 첨단산업과 같은 성장산업에서 고급인력을 양성하고 기술력을 확보함으로써 기업의 대내외적인 경쟁력을 확보할 수 있게 된다. 또한 종업원의 동기를 부여함으로써 임직원의 잠재적인 주주화를 통해 주인의식고취 및 책임경영을 실현 시킨다. 본 연구는 주식보상시스템의 도입에 따른 회계변수평가모형이 기업가치를 평가하는데 유용한지를 검증하였으며 현행 기업회계기준에 의해 작성된 주식매입선택권이기업 지식자산의 형태로 자산화되었을 경우 기업가치 평가를 검증하였다. 연구 결과 회계변수들은 기업가치를 평가하는데 유용한 측정치들이었으나 스톡옵션 부여와 관련된 주식매입선택권의 경우 현행 기업회계기준 방법에 의하였을 경우에는 주식매입선택권과 주식보상비용 모두 유의하지 않은 것으로 나타났다. 추가적으로 자산화 된 주식매입선택권의 경우 유의한 양(+)의 값으로서 기업 가치를 평가하는데 유의한 결과임을 지적하였다. 이는 투자자들이 기업 가치를 평가하는데 있어서 주식매입선택권을 현행 기업회계기준의 방법으로 처리하는 것보다 자산화 시킨 후 스톡옵션의 효익 지속기간 동안 상각하는 것이 기업가치를 평가하는데 더 유용한 방법이라는 점을 가지고 있다는 것을 나타낸다.

  • PDF

향상된 스틱-슬립 마찰 모델을 이용한 스마트 구조물의 마이크로 위치제어 (Micro-positioning of a Smart Structure using an Enhanced Stick-slip Model)

  • 이철희;장민규;최승복
    • 한국소음진동공학회:학술대회논문집
    • /
    • 한국소음진동공학회 2008년도 추계학술대회논문집
    • /
    • pp.230-236
    • /
    • 2008
  • In this paper, a model-based stick-slip compensation for the micro-positioning is proposed using an enhanced stick-slip model based on statistical rough surface contact model. The smart structure is comprised with PZT (lead (Pb) zirconia (Zr) Titanate (Ti)) based stack actuator incorporating with the PID (Proportional-Integral-Derivative) control algorithm, mechanical displacement amplifier and positioning devices. For the stick-slip compensation, the elastic-plastic static friction model is used considering the elastic-plastic asperity contact in the rough surfaces statistically. Mathematical model of system for the positioning apparatus was derived from the dynamic behaviors of structural parts. PID feedback control algorithms with the developed stick-slip model as well as feedforward friction compensator are formulated for achieving the accurate positioning performance. Experimental results are provided to show the performances of friction control using the developed positioning apparatus.

  • PDF

향상된 스틱-슬립 마찰 모델을 이용한 스마트 구조물의 마이크로 위치제어 (Micro-positioning of a Smart Structure Using an Enhanced Stick-slip Model)

  • 이철희;장민규;최승복
    • 한국소음진동공학회논문집
    • /
    • 제18권11호
    • /
    • pp.1134-1142
    • /
    • 2008
  • In this paper, a model-based stick-slip compensation for the micro-positioning is proposed using an enhanced stick-slip model based on statistical rough surface contact model. The smart structure is comprised with PZT(lead (Pb) zirconia(Zr) Titanate(Ti)) based stack actuator incorporating with the PID(proportional-integral-derivative) control algorithm, mechanical displacement amplifier and positioning devices. For the stick-slip compensation, the elastic-plastic static friction model is used considering the elastic-plastic asperity contact in the rough surfaces statistically. Mathematical model of system for the positioning apparatus was derived from the dynamic behaviors of structural parts. PID feedback control algorithms with the developed stick-slip model as well as feedforward friction compensator are formulated for achieving the accurate positioning performance. Experimental results are provided to show the performances of friction control using the developed positioning apparatus.