• 한국음향학회:학술대회논문집
• /
• 한국음향학회 2000년도 하계학술발표대회 논문집 제19권 1호
• /
• pp.119-122
• /
• 2000

In this paper, we implement an elementary system to correct accent, pronunciation, and intonation in English spoken by non-native English speakers. In case of the accent evaluation, energy and pitch information are used to find stressed syllables, and then we extract the segment information of input patterns using a dynamic time warping method to discriminate and evaluate accent position. For the pronunciation evaluation. we utilize the segment information using the same algorithm as in accent evaluation and calculate the spectral distance measure for each phoneme between input and reference. For the intonation evaluation. we propose nine pattern of slope to estimate pitch contour, then we grade test sentences by accumulated error obtained by the distance measure and estimated slope. Our result shows that 98 percent of accent and 71 percent of pronunciation evaluation agree with perceptual measure. As the result of the intonation evaluation. system represent the similar order of grade for the four sentences having different intonation patterns compared with perceptual evaluation.

• 방송공학회논문지
• /
• 제7권2호
• /
• pp.168-180
• /
• 2002

This paper proposes a novel method to detect unauthorized copies of digital images. This copy detection scheme can be used as either an alternative approach or a complementary approach to watermarking. A test image is reduced to 8$\times$8 sub-image by intensity averaging, and the AC coefficients of its discrete cosine transform (DCT) are used to compute distance from those generated from the query image, of which a user wants to find copies. Copies may be Processed to avoid copy detection or enhance image quality. We show ordinal measure of DCT coefficients, which is based on relative ordering of AC magnitude values and using distance metrics between two rank permutations, are robust to various modifications of the original image. The optimal threshold selection scheme using the maximum a posteriori (MAP) criterion is also addressed.

• 한국지능시스템학회논문지
• /
• 제12권6호
• /
• pp.583-588
• /
• 2002

Recently, Szmidt and Kacprzyk[Fuzzy Sets and Systems 118(2001) 467-477] proposed a non-probabilistic-type entropy measure for intuitionistic fuzzy sets. Tt is a result of a geometric interpretation of intuitionistic fuzzy sets and uses a ratio of distances between them. They showed that the proposed measure can be defined in terms of the ratio of intuitionistic fuzzy cardinalities: of $F\bigcapF^c and F\bigcupF^c$, while applying the Hamming distances. In this note, while applying the Euclidean distances, it is also shown that the proposed measure can be defined in terms of the ratio of some function of intuitionistic fuzzy cardinalities: of $F\bigcapF^c and F\bigcupF^c$.

• ETRI Journal
• /
• 제32권5호
• /
• pp.795-800
• /
• 2010

Embedding a large vocabulary speech recognition system in mobile devices requires a reduced acoustic model obtained by eliminating redundant model parameters. In conventional optimization methods based on the minimum description length (MDL) criterion, a binary Gaussian tree is built at each state of a hidden Markov model by iteratively finding and merging similar mixture components. An optimal subset of the tree nodes is then selected to generate a downsized acoustic model. To obtain a better binary Gaussian tree by improving the process of finding the most similar Gaussian components, this paper proposes a new distance measure that exploits the difference in likelihood values for cases before and after two components are combined. The mixture weight of Gaussian components is also introduced in the component merging step. Experimental results show that the proposed method outperforms MDL-based optimization using either a Kullback-Leibler (KL) divergence or weighted KL divergence measure. The proposed method could also reduce the acoustic model size by 50% with less than a 1.5% increase in error rate compared to a baseline system.

• 국제물리치료학회지
• /
• 제7권1호
• /
• pp.965-971
• /
• 2016

The purpose of this study was to investigate the effects of core strengthening training on baseball throwing. A total of 14 subjects were recruited from among middle school baseball players. The main outcome measures were as follows: speed guns were used to measure the velocity of baseballs thrown; scored targets were used to measure throwing accuracy; and 50m measuring tapes were used to measure throwing distances. It was found that core strengthening training improved the velocity of baseballs thrown and throwing accuracy and distance. Thus, core strengthening training is effective for improving the throwing ability of baseball players.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2002년도 추계학술대회 및 정기총회
• /
• pp.13-16
• /
• 2002

Recently, Szmidt and Kacprzyk[Fuzzy Sets and Systems 118(2001) 467-477] Proposed a non-probabilistic-type entropy measure for intuitionistic fuzzy sets. It is a result of a geometric interpretation of intuitionistic fuzzy sets and uses a ratio of distances between them. They showed that the proposed measure can be defined in terms of the ratio of intuitionistic fuzzy cardinalities: of F∩F$\^$c/ and F∪F$\^$c/, while applying the Hamming distances. In this note, while applying the Euclidean distances, it is also shown that the proposed measure can be defined in terms of the ratio of some function of intuitionistic fuzzy cardinalities: of F∩F$\^$c/ and F∪F$\^$c/.

• 한국정보통신학회논문지
• /
• 제16권3호
• /
• pp.615-625
• /
• 2012

운동자들의 운동 정보를 측정하기 위하여 스마트 폰의 운동 애플리케이션들은 GPS장치에서 얻은 정보들을 사용한다. 이러한 애플리케이션에서 사용자에게 제공하는 운동정보는 뛰거나 걸은 거리, 시간, 칼로리 소모량, 평균 속도 등 이다. 이들 중 운동한 거리는 모든 정보의 바탕이 되므로 정확한 측정이 필요하다. 그러나 현재 사용되는 거리 측정법은 지구를 구 또는 타원으로 가정하여 계산하기 때문에 실제 운동거리와는 오차가 생기게 된다. 실제로 지구의 표면은 경사로 이루어져 있기 때문이다. 본 논문에서는 이 오차를 보정하여 지형의 경사도를 반영한 새로운 거리측정 알고리즘을 제안한다. 제한된 알고리즘의 성능을 평가하기 위하여 스마트 폰을 기반으로 한 운동 라이프가이드 시스템을 구축하였다. 실험을 통하여 제안된 알고리즘이 보다 정확한 운동 거리 측정 정보를 제공함을 보인다.

• Communications for Statistical Applications and Methods
• /
• 제15권2호
• /
• pp.229-234
• /
• 2008

A Cook-type distance is considered for investigating the influence of observations in constrained regression models. Its exact sampling distribution is derived, which is used for judging whether each observation is influential or not. A numerical example is provided for illustration.

• 대한수학회보
• /
• 제36권2호
• /
• pp.287-303
• /
• 1999

The general solution of the functional equation f1(pr, qs) + f2(ps, qr) = g(p,q) + h(r,s) for p, q, r, s $\in$] 0, 1[will be investigated without any regularity assumptions on the unknown functions f1, f2, g, h:]0.1[->R.

• 한국통신학회논문지
• /
• 제18권10호
• /
• pp.1422-1432
• /
• 1993

HCNN(Hidden Control Neural Network)은 신경회로망에 의한 비선형 예측과 HMM의 segmentation 기능을 접합시킨 신경회로망 모델로서, 시간에 따라 입출력 사상 함수를 변화시킴으로써 음성 신호를 잘 모델링할 수 있도록 되어 있다. 본 논물에서는 첫째, HCNN의 성능이 HMM보다 우수함을 보이고, 둘째로, HCNN에서의 예측 오차 측정에 적절한 거리 측도를 이용하기 위해 가중거리가 도입된 HCNN을 제안하여, 화자 독립 음성 인식에 있어 그 성능이 우수함을 보였다. 여기서 가중거리는 음성 특징 벡터 각 구성 성분의 분산도 차이를 고려한 거리이다. 화자 독립 숫자음 인식 실험 결과, 유클리드 저리를 이용한 HCNN에 대해 95%의 인식율을 얻었는데, 이는 HMM에 비해 1.28% 높은 결과로서, 확률적인 제한이 가해진 HMM에 비해 시스템의 동작인 모델링을 이용한 HCNN이 더 우수함을 알 수 있다. 또한 가중거리를 이용한 CNN에 대해서는 97.35%의 인식율을 얻었는데, 이는 유클리드 거리를 이용한HCNN에 비해 2.3%가 향상된 결과이다. 가중 거리를 도입한 HCHN의 경우에 더 높은 인식율을 얻은 이유는, 오인식이 많이 되는 화자의 인식율을 높임으로써 화자간의 인식율차가 감소하게 되기 때문임을 알 수 있었고, 따라서 화자 독립 음성인식에 가중거리를 도입한 HCNN이 보다 적합합을 알 수 있다.