• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• 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.

• Journal of Digital Convergence
• /
• v.5 no.2
• /
• pp.37-45
• /
• 2007

A lot of organizations have been recognized innovative activities as the required process for organizational effectiveness and efficiency in those. Especially, the perceptual scope of innovation indisputability has been extended to the central and local government, and the public organization, which ultimately have the goal of public benefits. This study is to investigate the feasibility of the assessment elements consisting of framework for making a diagnosis of the level of administration innovation of local government. The elements of framework are such seven elements as innovative leadership, innovation vision and strategies, systematic infrastructure, innovative problems, innovation management, education and learning of innovation, and the perceptual level of members. The research results can provide the implications to not only local governments but also the public policy organizations who wish to extract the innovative problems and diagnose the innovation level of themselves.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.522-524
• /
• 2019

In spite of a rapid development in the quality of built-in mobile cameras, their some physical restrictions hinder them to achieve the satisfactory results of digital single lens reflex (DSLR) cameras. In this work we propose an end-to-end deep learning method to translate ordinary images by mobile cameras into DSLR-quality photos. The method is based on the framework of generative adversarial networks (GANs) with several improvements. First, we combined the U-Net with DenseNet and connected dense block (DB) in terms of U-Net. The Dense U-Net acts as the generator in our GAN model. Then, we improved the perceptual loss by using the VGG features and pixel-wise content, which could provide stronger supervision for contrast enhancement and texture recovery.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.1
• /
• pp.30-37
• /
• 2022

This paper compares and evaluates model performance from two perspectives according to the learning target and network structure for training Deep Neural Network (DNN)-based speech enhancement models in the frequency domain. In this case, spectrum mapping and Time-Frequency (T-F) masking techniques were used as learning targets, and a real network and a complex network were used for the network structure. The performance of the speech enhancement model was evaluated through two objective evaluation metrics: Perceptual Evaluation of Speech Quality (PESQ) and Short-Time Objective Intelligibility (STOI) depending on the scale of the dataset. Test results show the appropriate size of the training data differs depending on the type of networks and the type of dataset. In addition, they show that, in some cases, using a real network may be a more realistic solution if the number of total parameters is considered because the real network shows relatively higher performance than the complex network depending on the size of the data and the learning target.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.4
• /
• pp.819-833
• /
• 2013

Computing global features based on local features using a bio-inspired framework has shown promising performance. However, for some tough applications with large intra-class variances, a single local feature is inadequate to represent all the attributes of the images. To integrate the complementary abilities of multiple local features, in this paper we have extended the efficacy of the bio-inspired framework, HMAX, to adapt heterogeneous features for global feature extraction. Given multiple global features, we propose an approach, designated as parameterized metric learning, for high dimensional feature fusion. The fusion parameters are solved by maximizing the canonical correlation with respect to the parameters. Experimental results show that our method achieves significant improvements over the benchmark bio-inspired framework, HMAX, and other related methods on the Caltech dataset, under varying numbers of training samples and feature elements.

• Journal of Information Processing Systems
• /
• v.13 no.1
• /
• pp.8-25
• /
• 2017

This survey paper explores the application of multimodal feedback in automated systems for motor learning. In this paper, we review the findings shown in recent studies in this field using rehabilitation and various motor training scenarios as context. We discuss popular feedback delivery and sensing mechanisms for motion capture and processing in terms of requirements, benefits, and limitations. The selection of modalities is presented via our having reviewed the best-practice approaches for each modality relative to motor task complexity with example implementations in recent work. We summarize the advantages and disadvantages of several approaches for integrating modalities in terms of fusion and frequency of feedback during motor tasks. Finally, we review the limitations of perceptual bandwidth and provide an evaluation of the information transfer for each modality.

• Speech Sciences
• /
• v.5 no.2
• /
• pp.7-16
• /
• 1999

Starting as a poet, I learned about the sounds of words with David Abercrombie. Then, remembering my background in physics, I moved to studying acoustic phonetics and speech synthesis. From there I learned about psychology and how. to test perceptual theories. A meeting with a physiologist led to work on the use of the respiratory muscles in speech. Later I landed in Africa teaching English phonetics and learning about African languages. When I went to UCLA to set up a lab I was able to find bright students who helped make computer models of the vocal tract and taught me linguistic theory. And I was able to continue wandering around the world, describing the sounds of a wide range of languages.

• Journal of the Korea Convergence Society
• /
• v.11 no.1
• /
• pp.131-139
• /
• 2020

Gamers switch their games to a new when get bored or encounter more attractive ones. Switching cost varies by gamers and depends on how they are satisfied with their current game. This study evaluates the satisfaction with current games as the miltiple basic psychological need in the self-determination theory and suggests 'needs-costs' causality research model that explain the variety of gamer's switching behavior. As the empirical test to domestic mobile gamers, the autonomy fulfillment to current game affect reversely with those of autonomy and relatedness. Those relationships between need satisfaction and perceptual switching cost vary according to their age and game genre preference. The results would be applied to understand gamers' switching behavior.

• PNF and Movement
• /
• v.6 no.3
• /
• pp.19-28
• /
• 2008

Purpose : The objective of this study was to determine efficacy of sleep-dependent motor learning. Methods : This is a literature study with books and internet. We searched the PubMed, Science Direct, KISS and DBpia. Key words were Sleep-dependent, motor learning, RAM and LTP. Results : Procedural memory, like declarative memory, undergoes a slow, time-dependent period of consolidation. A process has recently been described wherein performance on some procedural task improves with the mere passage of time and has been termed "enhancement". Some studies have reported that the consolidation/enhancement of perceptual and motor skill is dependent on sleep. Specially, rapid-eye-movement(REM) sleep seems to benefit procedural aspects of memory. Conclusion : Motor learning is very important for CNS injury patients. And also distribution of practice sessions is important because REM sleep is to benefit procedural aspects of memory consolidation.

• International Journal of Contents
• /
• v.13 no.4
• /
• pp.16-22
• /
• 2017

The purpose of this study was to investigate the daily life experiences of medical students and to explore gender differences in these experiences using the Experience Sampling Method (ESM) as the method. The instrument, the Experience Sampling Form (ESF), consisted of questions on the external and internal experiences of the respondents. Data were collected from 2,035 ESFs by 91 students (male=52, female=39) at three medical schools for one week. The data was analyzed using the statistical tests of the t-test and ${\chi}^2$ test. Activity places were significantly different by gender (${\chi}^2=16.576$, p=.001). Males spent more time in learning places such as schools, libraries, etc., whereas females spent their time in personal places, including their homes, dormitories, etc. Males undertook more learning activities than did females, and females undertook more social/leisure activities and basic life activities than did male students (${\chi}^2=18.753$, p=.001). They were in a learning place and performing learning activities. There were significant perceptual differences between males and females about their flow levels, competency levels, and difficulty levels, based on the activity type. These results can help us to understand the daily lives of medical students and can be useful in developing counseling programs and educational activities for students.