• 대한음성학회지:말소리
• /
• 제51호
• /
• pp.71-84
• /
• 2004

In this paper, we propose the automatic speech database verification method(or called automatic verification) based on confidence measure for a large speech database. This method verifies the consistency between given transcription and speech using the confidence measure. The automatic verification process consists of two stages : the word-level likelihood computation stage and multi-level likelihood ratio computation stage. In the word-level likelihood computation stage, we calculate the word-level likelihood using the viterbi decoding algorithm and make the segment information. In the multi-level likelihood ratio computation stage, we calculate the word-level and the phone-level likelihood ratio based on confidence measure with anti-phone model. By automatic verification, we have achieved about 61% error reduction. And also we can reduce the verification time from 1 month in manual to 1-2 days in automatic.

• Communications for Statistical Applications and Methods
• /
• 제30권1호
• /
• pp.49-63
• /
• 2023

A lot of studies on the summary measures of predictive strength of categorical response models consider the likelihood ratio index (LRI), also known as the McFadden-R², a better option than many other measures. We propose a simple modification of the LRI that adjusts for the effect of the number of response categories on the measure and that also rescales its values, mimicking an underlying latent measure. The modified measure is applicable to both binary and ordinal response models fitted by maximum likelihood. Results from simulation studies and a real data example on the olfactory perception of boar taint show that the proposed measure outperforms most of the widely used goodness-of-fit measures for binary and ordinal models. The proposed R² interestingly proves quite invariant to an increasing number of response categories of an ordinal model.

• 디지털융복합연구
• /
• 제10권6호
• /
• pp.219-224
• /
• 2012

통신 모바일 단말기에서 어휘 인식 시스템은 부정확한 어휘로부터 음소 특징을 추출하기 때문에 음소를 인식하지 못하거나 유사한 음소 오인식 오류로 인한 낮은 인식률의 문제점을 가진다. 이러한 문제를 해결하기 위해서, 본 논문에서는 입력 음소는 음소 유사율 처리를 통해 음소 사이의 거리를 측정하여 수치로 나타내고, 신뢰도 측정을 통하여 인식되어진 결과를 확인하는 시스템을 제안하였다. 이로 인해 부정확한 어휘 제공으로 인한 오인식 오류를 최소화하였으며 음소 유사율과 신뢰도를 이용하여 오류 보정율을 구하였다. 기존 방법인 에러 패턴 학습을 이용한 시스템과 의미기반을 이용한 시스템의 성능 평가 결과 2.7%의 인식 향상율을 보였다.

• 음성과학
• /
• 제9권1호
• /
• pp.49-59
• /
• 2002

This paper concerns an effective text-dependent speaker verification method to increase the performance of speaker verification. While various speaker verification methods have already been developed, their effectiveness has not yet been formally proven in terms of achieving acceptable performance levels. This paper proposes a weighted likelihood procedure along with a confidence measure based on subword-based text-dependent speaker verification. Our aim is to remedy the low performance problem in speaker verification by exploring a means to strengthen the verification likelihood via subword-based hypothesis criteria and weighted likelihood method. Experimental results show that the proposed speaker verification method outperforms that of the speaker verification scheme without using the proposed decision by a factor of up to 1.6 times. From these results, the proposed speaker verification method is shown to be very effective and to achieve a reliable performance.

• 대한예방의학회:학술대회논문집
• /
• 대한예방의학회 1994년도 교수 연수회(역학)
• /
• pp.154-157
• /
• 1994

The evaluation of diagnostic tests attempts to obtain one or more statistical parameters which can indicate the intrinsic diagnostic utility of a test. Sensitivity. specificity and predictive value are not appropriate for this use. The likelihood ratio has been proposed as a useful measure when using a test to diagnose one of two disease states (e.g. disease present or absent). In this paper, we generalize the likelihood ratio concept to a situation in which the goal is to diagnose one of several non-overlapping disease states. A formula is derived to determine the post-test probability of a specific disease state. The post-test odds are shown to be related to the pre-test odds of a disease and to the usual likelihood ratios derived from considering the diagnosis between the target diagnosis and each alternate in turn. Hence, likelihood ratios derived from comparing pairs of diseases can be used to determine test utility in a multiple disease diagnostic situation.

• Communications for Statistical Applications and Methods
• /
• 제9권3호
• /
• pp.715-723
• /
• 2002

This paper is to show a clustering application of a density estimation method that utilizes the Gaussian mixture model. We define "closeness measure" as a clustering criterion to see how close given two Gaussian components are. Closeness measure is defined as the ratio of log likelihood between two Gaussian components. According to simulations using artificial data, the clustering algorithm turned out to be very powerful in that it can correctly determine clusters in complex situations, and very flexible in that it can produce different sizes of clusters based on different threshold valuesold values

• 가정과삶의질연구
• /
• 제10권1호통권19호
• /
• pp.131-138
• /
• 1992

Regression analysis has become a standard statistical tool in the behavioral science. Because of its widespread popularity. regression has been often misused. Such is the case when the dependent variable is a qualitative measure rather than a continuous, interval measure. Regression estimates with a qualitative dependent variable does not meet the assumptions underlying regression. It can lead to serious errors in the standard statistical inference. Logit model is recommended as alternatives to the regression model for qualitative dependent variables. Researchers can employ this model to measure the relationship between independent variables and qualitative dependent variables without assuming that logit model was derived from probabilistic choice theory. Coefficients in logit model are typically estimated by the method of Maximum Likelihood Estimation in contrast to ordinary regression model which estimated by the method of Least Squares Estimation. Goodness of fit in logit model is based on the likelihood ratio statistics and the t-statistics is used for testing the null hypothesis.

• 대한음성학회지:말소리
• /
• 제60호
• /
• pp.165-180
• /
• 2006

In this paper, we present several confidence measures (CM) for speech recognition systems to evaluate the reliability of recognition results. We propose heuristic CMs such as mean log-likelihood score, N-best word log-likelihood ratio, likelihood sequence fluctuation and likelihood ratio testing(LRT)-based CMs using several types of anti-models. Furthermore, we propose new algorithms to add weighting terms on phone-level log-likelihood ratio to merge word-level log-likelihood ratios. These weighting terms are computed from the distance between acoustic models and knowledge-based phoneme classifications. LRT-based CMs show better performance than heuristic CMs excessively, and LRT-based CMs using phonetic information show that the relative reduction in equal error rate ranges between $8{\sim}13%$ compared to the baseline LRT-based CMs. We use the support vector machine to fuse several CMs and improve the performance of utterance verification. From our experiments, we know that selection of CMs with low correlation is more effective than CMs with high correlation.

• 대한토목학회논문집
• /
• 제33권3호
• /
• pp.937-945
• /
• 2013

홍수범람도의 정확성은 입력자료, 모형변수, 모델접근방법 등을 포함한 전반적인 구축과정에 포함된 모든 변수들로부터 전달되는 불확실성에 의해 결정된다. 본 연구의 목적은 미국 Missouri주 Boonville시에 위치한 Missouri 강에 대한 홍수범람도 구축과정에서 모델 변수들 가운데 주 요소 (흐름조건, 조도계수)로부터 발생하는 불확실성을 조사하는 것이다. 본 연구를 수행하기 위하여 홍수범람면적의 불확실성 구간을 정량화하기 위한 GLUE (generalized likelihood uncertainty estimation)를 이용하였다. GLUE 수행과정에서 불확실성 구간은 두 개의 우도함수를 선택함으로 산정되었는데 선택된 우도함수는 제곱오차 합의 역 (1/SSE)과 절대오차 합의 역 (1/SAE)이다. GLUE의 결과는 제곱오차 합의 역에 의한 우도측정이 절대오차 합의 역에 의한 우도측정보다 관측 자료에 더 민감하였고, 두 개의 변수에 포함된 불확실성은 관측 자료의 약 2 %에 해당하는 홍수범람면적의 불확실성 구간에 전달되었다. 이러한 결과를 토대로, 본 연구는 홍수의 특성을 알아내는데 중요한 역할을 할 것으로 기대된다.

• 한국음향학회지
• /
• 제22권3호
• /
• pp.194-201
• /
• 2003

음성인식에서 신뢰도 측정이란 인식된 결과에 대한 신뢰 여부를 결정하는 것이다. 신뢰도는 프레임을 음소 및 단어 수준으로 통합하여 측정된다. 단어 인식의 경우, 신뢰도를 이용하여 인식 결과와 미등록 어휘를 검증한다. 따라서 이러한 후처리를 통해 이를 인식 결과로 승인하지 않음으로써 성능을 높일 수 있다. 본 논문에서는 기존의 신뢰도 측정 방법인 로그 유사도 비를 수정하여 신뢰도를 측정하였다. 제안된 방법은 프레임 수준에서 음소 수준으로 신뢰도를 통합할 때 로그 유사도 비가 음수인 것만을 누적하는 것이다. 단어 인식기의 인식 결과에 대한 검증 성능을 기존의 방법과 비교한 결과, CAR (Correct Acceptance Ratio)이 90%인 지점에서 FAR (False Acceptance Ratio)을 미등록 어휘에 대해서는 약 3.49%, 오인식에 대해서는 15.25% 감소시킬 수 있었다