• 제목/요약/키워드: state-duration model

검색결과 113건 처리시간 0.021초

결정트리기반 음성인식 시스템에서의 음소지속시간 사용방법 (A phoneme duration modeling in a speech recognition system based on decision tree state tying)

  • 구명완;김호경
    • 대한음성학회:학술대회논문집
    • /
    • 대한음성학회 2002년도 11월 학술대회지
    • /
    • pp.197-200
    • /
    • 2002
  • In this paper, we propose a phoneme duration modeling in a speech recognition system based on disicion tree state tying. We assume that phone duration has a Gamma distribution. In a training mode, we model mean and variance of each state duration in context-independent phone model based on decision tree state tying. In a recognition mode, we get mean and variance of each context-dependent phone duration form state duration information obtaind during training mode. We make a comparative study of the proposed meth with conventinal methods. Our method results in good performance compared with conventional methods.

  • PDF

A Model To Enhance Site-Specific Estimation Of Wetness Duration Using A Wind Speed Correction

  • Kim, Kwang-Soo;S.Elwynn Taylor;Mark L.Gleason;Kenneth J.Koehler
    • 한국농림기상학회:학술대회논문집
    • /
    • 한국농림기상학회 2001년도 춘계 학술발표논문집
    • /
    • pp.163-166
    • /
    • 2001
  • One of the most important factors influencing the outbreak and severity of foliar diseases is the duration of wetness from dew deposition, rainfall, or irrigation. Models may provide good alternatives for assessing leaf wetness duration (LWD) without the labor, cost, and inconvenience of making measurements with sensors.(omitted)

  • PDF

음소길이를 고려한 3-State Hidden Markov Model 에 의한 한국어 음소인식 (Korean Phoneme Recognition Using duration-dependent 3-State Hidden Markov Model)

  • 유현창;이희정;박병철
    • 한국음향학회지
    • /
    • 제8권1호
    • /
    • pp.81-87
    • /
    • 1989
  • 본 논문은 Markov 모델에 의한 효과적인 한국어 음소모델 작성방식과 인식에 대하여 기술한다. hidden Markov 모델은 음성신호 고유의 비정상성을 효과적으로 모델화할 수 있다. 본 논문에서는 음소의 일련의 변화하는 특성, 즉 천이-안정-천이의 변화를 나타내기 위하여 3상태 음소모델을 제안한다. 또한 음소길이가 인식성능에 영향을 미치는 중요한 요소임을 밝히고 길이를 고려한 3상태 hidden Markov 모델을 사용하여 인식률을 개선시킬 수 있음을 보였다.

  • PDF

An improvement on the concrete exothermic models considering self-temperature duration

  • Zhu, Zhenyang;Chen, Weimin;Qiang, Sheng;Zhang, Guoxin;Liu, Youzhi
    • Computers and Concrete
    • /
    • 제19권6호
    • /
    • pp.659-666
    • /
    • 2017
  • Based on the Arrhenius equations, several hydration exothermic models that precisely calculate the influence of concrete's self-temperature duration on its hydration exothermic rate have been presented. However, the models' convergence is difficult to achieve when applied to engineering projects, especially when the activation energy of the Arrhenius equation is precisely considered. Thus, the models' convergence performance should be improved. To solve this problem and apply the model to engineering projects, the relationship between fast iteration and proper expression forms of the adiabatic temperature rise, the coupling relationship between the pipe-cooling and hydration exothermic models, and the influence of concrete's self-temperature duration on its mechanical properties were studied. Based on these results, the rapid convergence of the hydration exothermic model and its coupling with pipe-cooling models were achieved. The calculation results for a particular engineering project show that the improved concrete hydration exothermic model and the corresponding mechanical model can be suitably applied to engineering projects.

Estimation of Leaf Wetness Duration Using An Empirical Model

  • Kim, Kwang-Soo;S.Elwynn Taylor;Mark L.Gleason;Kenneth J.Koehler
    • 한국농림기상학회:학술대회논문집
    • /
    • 한국농림기상학회 2001년도 춘계 학술발표논문집
    • /
    • pp.93-96
    • /
    • 2001
  • Estimation of leaf wetness duration (LWD) facilitates assessment of the likelihood of outbreaks of many crop diseases. Models that estimate LWD may be more convenient and grower-friendly than measuring it with wetness sensors. Empirical models utilizing statistical procedures such as CART (Classification and Regression Tree; Gleason et al., 1994) have estimated LWD with accuracy comparable to that of electronic sensors.(omitted)

  • PDF

Walking load model for single footfall trace in three dimensions based on gait experiment

  • Peng, Yixin;Chen, Jun;Ding, Guo
    • Structural Engineering and Mechanics
    • /
    • 제54권5호
    • /
    • pp.937-953
    • /
    • 2015
  • This paper investigates the load model for single footfall trace of human walking. A large amount of single person walking load tests were conducted using the three-dimensional gait analysis system. Based on the experimental data, Fourier series functions were adopted to model single footfall trace in three directions, i.e. along walking direction, direction perpendicular to the walking path and vertical direction. Function parameters such as trace duration time, number of Fourier series orders, dynamic load factors (DLFs) and phase angles were determined from the experimental records. Stochastic models were then suggested by treating walking rates, duration time and DLFs as independent random variables, whose probability density functions were obtained from experimental data. Simulation procedures using the stochastic models are presented with examples. The simulated single footfall traces are similar to the experimental records.

Development of A Leaf Wetness Duration Model Using a Fuzzy Logic System

  • Kim, K.S.;S.E.Taylor;M.L.Gleason
    • 한국농림기상학회:학술대회논문집
    • /
    • 한국농림기상학회 2003년도 춘계 학술발표논문집
    • /
    • pp.50-53
    • /
    • 2003
  • Models have been developed to estimate leaf wetness duration (LWD) using conventional weather observations, e.g., air temperature, water vapor pressure, and wind speed, which are relatively invariant over space (Pedro and Gillespie, 1982; Gleason et al., 1994; Francl and Panigrahi, 1997).(omitted)

  • PDF

다양한 데이터 트래픽을 갖는 이동 애드혹 네트워크용 라우팅 프로토콜의 성능 분석 (Performance Analysis of MANET Routing Protocols with Various Data Traffic)

  • 김기완
    • 반도체디스플레이기술학회지
    • /
    • 제20권2호
    • /
    • pp.67-72
    • /
    • 2021
  • MANET(Mobile Ad Hoc Network) is the structure in which a source node communicates with a destination node by establishing a route with neighbor nodes without using the existing wired or wireless network. Therefore, the routing protocol for MANET must correspond well to changes in the channel state of moving nodes, and should have simple operation, high reliability, and no routing loop. In this paper, the simulation was perform by using a traffic model with on/off two states provided by the NS-3 network simulator. Also, the duration of the ON state and the duration of the OFF state used the traffic where inter arrival time of data is irregular by generating random values with constant, exponential distribution, and Pareto distribution. The performance of the DSDV, OLSR, and AODV protocols was compare and analyzed using the generated traffic model.

유황곡선의 거동특성을 이용한 유역관리모형의 평가 (The Evaluation of Watershed Management Model using Behavioral Characteristics of Flow-duration Curve)

  • 김주철;이상진;신현호;황만하
    • 한국물환경학회지
    • /
    • 제25권4호
    • /
    • pp.573-579
    • /
    • 2009
  • The performance of Rainfall-Runoff Forecasting System (RRFS), the watershed management model for the Geum river basin, is evaluated based on the agreement between the simulated and observed hydrographs and the behavioral characteristics of the flow-duration curves. As a result, the simulated hydrographs are well agreed with the observed ones except high flow discharges. It is inferred that most of the errors in the simulated hydrographs are due to the misestimation of agricultural water use in $2^{nd}$ quarter and the discrepancy of the peak discharges in $3^{rd}$ quarter. It is however judged that RRFS would give the reliable runoff hydrographs from the point of view of continuous model application. And simulated flow-duration curves and flow-duration coefficients are also similar to the observed ones except flood flow region. From the above result it is confirmed that the construction of Yongdam dam improves the state of flow-duration curve at the Gongjoo station.

HMM 기반의 한국어 음성합성에서 지속시간 모델 파라미터 제어 (Control of Duration Model Parameters in HMM-based Korean Speech Synthesis)

  • 김일환;배건성
    • 음성과학
    • /
    • 제15권4호
    • /
    • pp.97-105
    • /
    • 2008
  • Nowadays an HMM-based text-to-speech system (HTS) has been very widely studied because it needs less memory and low computation complexity and is suitable for embedded systems in comparison with a corpus-based unit concatenation text-to-speech one. It also has the advantage that voice characteristics and the speaking rate of the synthetic speech can be converted easily by modifying HMM parameters appropriately. We implemented an HMM-based Korean text-to-speech system using a small size Korean speech DB and proposes a method to increase the naturalness of the synthetic speech by controlling duration model parameters in the HMM-based Korean text-to speech system. We performed a paired comparison test to verify that theses techniques are effective. The test result with the preference scores of 73.8% has shown the improvement of the naturalness of the synthetic speech through controlling the duration model parameters.

  • PDF