• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.1
• /
• pp.33-38
• /
• 2019

This paper proposes an effective recognition method of VPI patient's speech employing DNN-HMM-based speech recognition system, and evaluates the recognition performance compared to GMM-HMM-based system. The proposed method employs speaker adaptation technique to improve VPI speech recognition. This paper proposes to use simulated VPI speech for generating a prior model for speaker adaptation and selective learning of weight matrices of DNN, in order to effectively utilize the small size of VPI speech for model adaptation. We also apply Linear Input Network (LIN) based model adaptation technique for the DNN model. The proposed speaker adaptation method brings 2.35% improvement in average accuracy compared to GMM-HMM based ASR system. The experimental results demonstrate that the proposed DNN-HMM-based speech recognition system is effective for VPI speech with small-sized speech data, compared to conventional GMM-HMM system.

• Journal of The Korean Association For Science Education
• /
• v.36 no.4
• /
• pp.705-715
• /
• 2016

The purpose of this research is to analyze elementary students' attention characteristics through attention test and eye tracking on real science classes. The SMI's ETG(eye tracker glasses) mobile eye tracker was used to analyze the attention process of elementary students'. The sampling rate of the ETG is 30Hz. The participants of attention test were elementary 155 6th-grade elementary students and the participants for the eye-tracker were six 6th-grade male students. The eye movements were analyzed using the 'BeGaze Mobile Video Analysis Package' program. The results of this research are as follows. First, the attention test results of elementary students showed high correlation between selective attention and sustained attention (.85) and low correlation between selective attention and self-regulation (.32). Second, the attention types of elementary students were divided into four; attention, inattention, easygoing and hasty. Third, elementary students' attention were divided into top-down, bottom-up, default mode network through analysis of elementary students′ eye-movements during real science classes. Also their attention shift occurred frequently due to various reasons in real class situation. There were three reasons that made elementary students fail to handle knowledge-dependent top-down attention; 1) the cognitive failure of target caused by failing to focus attention, 2) the absence of prior knowledge on target object, 3) the analogical failure of prior knowledge. Finally, elementary students' attention process were schematized based on the analysis of students' eye movements and attention test. This research is expected to be utilized as basic data for developing effective teaching strategies, teaching-learning models and instructional materials.

• Science of Emotion and Sensibility
• /
• v.13 no.1
• /
• pp.47-60
• /
• 2010

Most of the researches about classification usually have used kNN(k-Nearest Neighbor), SVM(Support Vector Machine), which are known as learn-based model, and Bayesian classifier, NNA(Neural Network Algorithm), which are known as statistics-based methods. However, there are some limitations of space and time when classifying so many web pages in recent internet. Moreover, most studies of classification are using uni-gram feature representation which is not good to represent real meaning of words. In case of Korean web page classification, there are some problems because of korean words property that the words have multiple meanings(polysemy). For these reasons, LSA(Latent Semantic Analysis) is proposed to classify well in these environment(large data set and words' polysemy). LSA uses SVD(Singular Value Decomposition) which decomposes the original term-document matrix to three different matrices and reduces their dimension. From this SVD's work, it is possible to create new low-level semantic space for representing vectors, which can make classification efficient and analyze latent meaning of words or document(or web pages). Although LSA is good at classification, it has some drawbacks in classification. As SVD reduces dimensions of matrix and creates new semantic space, it doesn't consider which dimensions discriminate vectors well but it does consider which dimensions represent vectors well. It is a reason why LSA doesn't improve performance of classification as expectation. In this paper, we propose new LSA which selects optimal dimensions to discriminate and represent vectors well as minimizing drawbacks and improving performance. This method that we propose shows better and more stable performance than other LSAs' in low-dimension space. In addition, we derive more improvement in classification as creating and selecting features by reducing stopwords and weighting specific values to them statistically.