• Journal of KIISE:Software and Applications
• /
• v.33 no.5
• /
• pp.499-507
• /
• 2006

Recently human gait has been considered as a useful biometric supporting high performance human identification systems. This paper proposes a view-based pedestrian identification method using the dynamic silhouettes of a human body modeled with the Hidden Markov Model(HMM). Two types of gait models have been developed both with an endless cycle architecture: one is a discrete HMM method using a self-organizing map-based VQ codebook and the other is a continuous HMM method using feature vectors transformed into a PCA space. Experimental results showed a consistent performance trend over a range of model parameters and the recognition rate up to 88.1%. Compared with other methods, the proposed models and techniques are believed to have a sufficient potential for a successful application to gait recognition.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.5
• /
• pp.1243-1250
• /
• 2015

This paper presents an effective recognition method of VPI patient's speech for a VPI speech reconstruction system. Speaker adaptation technique is employed to improve VPI speech recognition. This paper proposes to use simulated speech for generating an initial model for speaker adaptation, in order to effectively utilize the small size of VPI speech for model adaptation. We obtain 83.60% in average word accuracy by applying MLLR for speaker adaptation. The proposed speaker adaptation method using simulated speech model brings 6.38% improvement in average accuracy. The experimental results demonstrate that the proposed speaker adaptation method is highly effective for developing recognition system of VPI speech which is not suitable for constructing large-size speech database.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.82-85
• /
• 1999

본 연구에서는 연속음성인식 시스템의 성능 향상을 위하여 음성의 채록환경 및 데이터량 등을 고려한 효과적인 언어모델 작성방법을 제안하고, 이를 항공편 예약시스템에 적용하여 성능 평가 실험을 실시한 결과 $91.6\%$의 인식률을 얻어 제안한 방법의 유효성을 확인하였다. 이를 위하여 소량의 200문장의 항공편 예약 텍스트 데이터를 이용하여 좀더 강건한 단어발생 확률을 가지도록 하기 위해 일반적으로 대어휘 연속음성인식에서 많이 이용되고 있는 단어 N-gram 언어모델을 도입하고 이를 다양한 발성환경을 고려하여 1,154문장으로 확장한 후 동일 문장'을 반복 학습하여 언어모델을 작성하였다. 인식에 있어서는 오인식과 문법적 오류를 최소화하기 위하여 forward - backward pass 방법의 stack decoding알고리즘을 이용하였다. 인식실험 결과, 평가용 3인의 200문장을 각 반복학습 회수에 따라 학습한 각 언어모델에 대해 평가한 결과, forward pass의 경우 평균 $84.1\%$, backward pass의 경우 평균 $91.6\%$의 문장 인식률을 얻었다. 또한, 반복학습 회수가 증가함에 따라 backward pass의 인시률의 변화는 없었으나, forward pass의 경우, 인식률이 반복회수에 따라 증가하다가 일정값에 수렴함을 알 수 있었고, 언어모델의 복잡도에서도 반복회수가 증가함에 따라 서서히 줄어들며 수렴함을 알 수 있었다. 이상의 결과로부터 소량의 텍스트 데이터를 이용한 제한된 태스크에서 언어모델을 작성할 때 반복학습 방법이 유효함을 확인할 수 있다.

• The Journal of the Acoustical Society of Korea
• /
• v.8 no.1
• /
• pp.81-87
• /
• 1989

This paper discribes the method associated with modeling of Korean phonemes. Hidden Markov models(HMM's) may be viewed as an effective technique for modeling the inherent nonstationarity of speech signal. We propose a 3-state phoneme model to represent the sequentially changing characteristics of phonemes, i.e., transition-to-stationary-to-transition. Also we clarify that the duration of a phoneme is an important factor to have an effect in recognition accuracy and show that improvement in recognition rate can be obtained by using duration-dependent 3-state hidden Markov models.

• The Journal of the Acoustical Society of Korea
• /
• v.11 no.3
• /
• pp.61-66
• /
• 1992

There have been many researches that uses neural network models for automatic speech recognition, but the main trend was finding the neural network models and learning rules appropriate to automatic speech recognition. However, the choice of the input speech parameter for the neural network as well as neural network model itself is a very important factor for the improvement of performance of the automatic speech recognition system using neural network. In this paper we select 6 speech parameters from surveys of the speech recognition papers which uses neural networks, and analyze the performance for the same data and the same neural network model. We use 8 sets of 9 Korean plosives and 18 sets of 8 Korean vowels. We use recurrent neural network and compare the performance of the 6 speech parameters while the number of nodes is constant. The delta cepstrum of linear predictive coefficients showed best result and the recognition rates are 95.1% for the vowels and 100.0% for plosives.

• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.29-32
• /
• 2000

본 논문에서는 음성인식 시스템의 음향모델 개선을 위한 기초적 연구로서, 문맥적인 요소를 필요로 하는 SSS(Successive State Splitting)와 필요로 하지 않는 SSS-free 알고리즘을 이용한 HMnet(Hidden Markov Network) 음향모델 작성방법에 대해 검토하고 작성한 음향모델을 한국어에 적용하여 그 유효성을 확인하였다. HMnet을 이용한 음소모델의 작성방법은 전체 학습 데이터에 대해서 각각 2개의 상태를 가지는 초기 모델을 작성한 후, 이를 시간과 문맥방향으로의 최대 분포를 가지는 상태를 재분할한 후 임의의 상태수가 될 때까지 상태분할을 계속적으로 수행케 하여 각 음소모델을 작성하게 된다. 작성한 HMnet 음향모델의 유효성을 확인하기 위해 ETRI 445 단어의 3인에 대한 화자종속 음소인식 실험을 수행하였다. 인식실험 결과, SSS 알고리즘을 이용한 화자종속실험의 경우 상태수 520에서 평균 $62.8\%$의 인식률을, SSS-free 알고리즘의 경우 상태수 420에서 평균 $64.2\%$의 인식률을 얻었다. 이 결과는 HMM을 이용한 경우(약$43.4\%$)보다 $20\%$이상의 인식률 향상을 보여 이 알고리즘의 유효성을 확인할 수 있었다. SSS와 SSS-free를 비교한 경우, SSS-free가 SSS보다 낮은 상태수에서 평균 $1.4\% 향상된 인식률을 보였다.

• Journal of the Korean Chemical Society
• /
• v.65 no.1
• /
• pp.37-47
• /
• 2021

In this study, the model cognition level of high school science-gifted students about the two types of acid-base models taught in secondary schools was analyzed. In order to find out the model cognition level of students, 12 items were developed based on the acid-base reaction and the dissociation reaction of acids and bases. The subjects of the study were 95 students of two science-gifted schools. As a result of the questionnaire analysis, model cognition levels were analyzed 6 levels in the context of consistency, inconsistency, and unexplainable scope of the two models. In the acid-base reaction item, the largest percentage of students cognized only understanding of the two models. In the acid-base dissociation reaction item, they understood the two models and perceived the 'Known Ignorance' that cognizes the limitations of one model. However, there was only one student who perceived the limitations of both models and all of the 'Unknown Ignorance' that the model could not explain. Through this, we argued that there is a need for educational efforts to raise the model cognition level of science-gifted students.

• Journal of The Korean Association For Science Education
• /
• v.37 no.1
• /
• pp.143-154
• /
• 2017

Science inquiry has long been emphasized in Korean science education. Scientific modeling is one of key practices in science inquiry with a potential to provide students with opportunities to develop their own explanations and knowledge thereafter. The purpose of this study is to investigate teacher's understanding of models in science and science teaching. A professional development program on Models (PDM) was developed and refined through three times of implementation while teachers' conceptions of models and modeling were examined. A total of 29 elementary and secondary teachers participated in this study. A survey based on model use of scientists in the history of science was developed and used to collect data and audio recordings of discussions among teachers and artifacts produced by the teachers during PDM were also collected. Three ways of ontological and two ways of epistemological understanding of models and modeling were found in teachers' ideas. After PDM, a quarter of the teachers changed their ontological understanding whereas very few changed their epistemological understanding. In contrast, more than two thirds of the teachers deepened and extended their ideas about using models and modeling in teaching. There were no clear relationships between teachers' understanding of models and ways and ideas about using models in science teaching. However, teachers' perceptions of school conditions were found to mediate their intention to use models in science teaching. The findings indicate possible approaches to professional development program content design and further research.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2001.11a
• /
• pp.849-853
• /
• 2001

본 논문에서는 연속적인 인간의 제스처 영상을 저차원 제스처 특징 공간과 HMM 이용하여 인식할 수 있는 방법에 대해 소개한다. 일반적으로 제스처 공간에서 모델 패턴들과 매칭하기 위해서는 모든 모델 영상과 연속적인 입력영상들간의 거리평가로 인식을 수행하게 된다. 여기서 제안한 방법은 연속성을 가진 모델영상들을 HMM로 포즈들의 시공간적 특성을 매칭에 이용하였다. 이 방법은 동작의 구분뿐만 인식결과를 학습에 이용할 수 있는 장점이 있다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2001.06a
• /
• pp.173-176
• /
• 2001

본 논문에서는 저차원 제스처 특징 공간에서 연속적인 인간의 제스처 영상을 계층적 클러스터링을 이용하여 인식할 수 있는 방법에 대해 소개한다. 일반적으로 제스처 공간에서 모델 패턴들과 매칭하기 위해서는 모든 모델 영상과 연속적인 입력영상들간의 거리평가로 인식을 수행하게 된다. 여기서 제안한 방법은 모델영상들을 연속성을 가진 클러스터로 분류하여 입력 영상과 계층적으로 비교할 수 있으며 동작에 관한 구체적 정보를 얻을 수 있다. 이 방법은 매칭 속도와 인식률을 개선하고 인식결과를 학습에 이용할 수 있는 장점이 있다.