• The Journal of the Acoustical Society of Korea
• /
• v.40 no.3
• /
• pp.234-240
• /
• 2021

In this paper, the mask-based speech enhancement is improved for effective speech recognition in noise environments. In the mask-based speech enhancement, enhanced spectrum is obtained by multiplying the noisy speech spectrum by the mask. The VoiceFilter (VF) model is used as the mask estimation, and the Spectrogram Inpainting (SI) technique is used to remove residual noise of enhanced spectrum. In this paper, we propose a combined loss to further improve speech enhancement. In order to effectively remove the residual noise in the speech, the positive part of the Triplet loss is used with the component loss. For the experiment TIMIT database is re-constructed using NOISEX92 noise and background music samples with various Signal to Noise Ratio (SNR) conditions. Source to Distortion Ratio (SDR), Perceptual Evaluation of Speech Quality (PESQ), and Short-Time Objective Intelligibility (STOI) are used as the metrics of performance evaluation. When the VF was trained with the mean squared error and the SI model was trained with the combined loss, SDR, PESQ, and STOI were improved by 0.5, 0.06, and 0.002 respectively compared to the system trained only with the mean squared error.

• International Area Studies Review
• /
• v.15 no.2
• /
• pp.199-223
• /
• 2011

This research would research about discount store's service quality of Korean and Chinese consumers' recognition and importance of commitment dimensions. Also, research about differences between word of mouth intention and relationship retention intention. Results of hypothesis are as follow. First, for service quality dimension that has effect on normative commitment, service quality dimension has positive effect over normative commitment especially in tangibility, reliability and responsiveness. Second, for service quality dimension that has effect on affective commitment, among dimensions, except tangibility, reliability, responsiveness, assurance and empathy have positive effect over affective commitment. Third, for service quality dimension that has effect on continuous commitment, among dimensions, tangibility and reliability have positive effect over continuous commitment. Fourth, for relationship between dimensions of commitment, affective commitment has positive effect over normative commitment while continuous commitment has positive effect over affective commitment. Fifth, dimensions of commitment has effect over relationship performance variables that are relationship retention intention and word of mouth intention.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.6
• /
• pp.370-378
• /
• 2019

The aim of this study was conducted to investigate the awareness and practice of personal hygiene and clinic hygiene of infection among physical therapist and to analyze the factors affecting it to provide basic data for the establishment of nosocomial infection management programs and policies in the physical therapist unit. In this study, 320 physical therapists were collected and analyzed. The study tool used a self-administered questionnaire to investigate general characteristics and awareness and practice of nosocomial infections. Responses were determined as 5-Likert scales and data were analysed using percentage, independent t-test, ANOVA. As a result of this study, 17.8% of infectious disease management departments were not found, and 41.6% of physical therapists were not educated about nosocomial infection. In addition, physical therapists with sufficient protective equipment for treatment were very low at 25.3%. Thus, in order to increase awareness and practice of nosocomial infection in the future, it is necessary to provide enough protective equipment for the treatment within the hospital, and it is considered that the nosocomial infection education of the physical therapist should be carried out regularly in the hospital itself.

• Korean Journal of Child Education & Care
• /
• v.18 no.4
• /
• pp.123-143
• /
• 2018

Objective: The purpose of this study was to investigate daycare center director's awareness of male teacher recruitment and need for effective male teacher recruitment. Methods: To this end, eight directors of child care centers with male teachers were selected as subjects of study. The data collection method was applied to the Focus Group Interview method, and a four interviews were conducted for two to two and a half hours. Results: After the interview data was analyzed, the contents were categorized into two major themes and six sub themes in awareness of male teacher recruitment by director of daycare center. The two major themes were (1) A vague fear of upcoming difficulties (2) The light and darkness of male teachers in the organization culture of childcare. Looking at the results, in a vague fear of upcoming difficulties theme includes administrative disadvantages, gender-related social atmosphere, and uncertainty about their role performance. Second, in the light and darkness theme includes women-centered organizational culture and adaptation, the vision of child care sites, and the role of male teachers at childcare sites. Next the contents were categorized into one major theme and four sub themes in need for effective male teacher recruitment by director of daycare center. The major theme was a male teacher's way into the daycare site, and sub five themes were expanding opportunities for child care experience and practices, a shift in the perception that it's not a man, it's an individual problem, maximizing the strengths of men, and improving the system. Conclusion/Implications: Based on these results, several specific implications of need for effective male teacher recruitment were suggested.

• Journal of Broadcast Engineering
• /
• v.23 no.6
• /
• pp.855-865
• /
• 2018

Sound event detection is one of the research areas to model human auditory cognitive characteristics by recognizing events in an environment with multiple acoustic events and determining the onset and offset time for each event. DCASE, a research group on acoustic scene classification and sound event detection, is proceeding challenges to encourage participation of researchers and to activate sound event detection research. However, the size of the dataset provided by the DCASE Challenge is relatively small compared to ImageNet, which is a representative dataset for visual object recognition, and there are not many open sources for the acoustic dataset. In this study, the sound events that can occur in indoor and outdoor are collected on a larger scale and annotated for dataset construction. Furthermore, to improve the performance of the sound event detection task, we developed a dual CNN structured sound event detection system by adding a supplementary neural network to a convolutional neural network to determine the presence of sound events. Finally, we conducted a comparative experiment with both baseline systems of the DCASE 2016 and 2017.

• Smart Media Journal
• /
• v.8 no.2
• /
• pp.58-65
• /
• 2019

Automatic text summarization is a process of shortening a text document by either extraction or abstraction. The abstraction approach inspired by deep learning methods scaling to a large amount of document is applied in recent work. Abstractive text summarization involves utilizing pre-generated word embedding information. Low-frequent but salient words such as terminologies are seldom included to dictionaries, that are so called, out-of-vocabulary(OOV) problems. OOV deteriorates the performance of Encoder-Decoder model in neural network. In order to address OOV words in abstractive text summarization, we propose a copy mechanism to facilitate copying new words in the target document and generating summary sentences. Different from the previous studies, the proposed approach combines accurate pointing information and selective copy mechanism based on bidirectional RNN and bidirectional LSTM. In addition, neural network gate model to estimate the generation probability and the loss function to optimize the entire abstraction model has been applied. The dataset has been constructed from the collection of abstractions and titles of journal articles. Experimental results demonstrate that both ROUGE-1 (based on word recall) and ROUGE-L (employed longest common subsequence) of the proposed Encoding-Decoding model have been improved to 47.01 and 29.55, respectively.

• Journal of Korean Society of Rural Planning
• /
• v.24 no.4
• /
• pp.135-146
• /
• 2018

A Visual landscape planning and management system has been introduced and implemented by each ministry so as to solve the problems of visual landscape destruction due to recognition on the value of natural landscape of beautiful territory and various development projects. At present, this system emphasizes the importance of the visual and perceptual aspect of the landscape however, there is a lack of techniques required for comprehensively predicting, evaluating, and managing it. Furthermore, sustainable landscape management after the completion of development projects has been inadequately carried out, as the focus has been only on consultation in the planning process of the development project in institutional performance. To this end, we presented objective and standardized criteria to predict and judge the effects of development projects on landscapes before project implementation. During the implementation of the development project, the influence of the visual landscape becomes accumulated in the construction progress stage. There is a need to identify the main viewpoints and to examine the continuous changes in the landscape-influencing factors, owing to the remarkable influences on the landscape, such as the change in the topography and the change caused by the artificial structure. During the stage of managing the influence on the visual landscape after the completion of the project, the influence on landscape should be monitored by measuring the change in the continuous landscape-influencing factors and determining the extent to which the actual reduction plan has been implemented. These processes should be performed continuously to maintain the quality of the visual landscape. The change in the landscape caused by the development project is shown to cause relatively greater visual damage than other factors composing the landscape owing to the influence of the artificial factors including the structure or the building. This shows that not only detailed examination of the visual impact before the development project but also continuous management is required during and after the development project. For this purpose, we derived eight landscape-influencing factors including form/shape, line, color, texture, scale/volume, height, skyline, and landscape control point. The proposed considering to be of high utilization in that it has a clear target of the landscape influencing factors.

• Journal of the Korea Computer Graphics Society
• /
• v.25 no.3
• /
• pp.11-20
• /
• 2019

In this study, a novel virtual reality (VR) experience environment is proposed for enabling walking adaptation of visually impaired people. The core of proposed VR environment is based on immersive walking interactions and deep learning based braille blocks recognition. To provide a realistic walking experience from the perspective of visually impaired people, a tracker-based walking process is designed for determining the walking state by detecting marching in place, and a controller-based VR white cane is developed that serves as the walking assistance tool for visually impaired people. Additionally, a learning model is developed for conducting comprehensive decision-making by recognizing and responding to braille blocks situated on roads that are followed during the course of directions provided by the VR white cane. Based on the same, a VR application comprising an outdoor urban environment is designed for analyzing the VR walking environment experience. An experimental survey and performance analysis were also conducted for the participants. Obtained results corroborate that the proposed VR walking environment provides a presence of high-level walking experience from the perspective of visually impaired people. Furthermore, the results verify that the proposed learning algorithm and process can recognize braille blocks situated on sidewalks and roadways with high accuracy.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.14 no.5
• /
• pp.19-30
• /
• 2018

Visual information understanding is known as one of the most difficult and challenging problems in the realization of machine intelligence. This paper proposes deriving visual verb and construction of ActionNet database as a video database for video semantic understanding. Even though development AI (artificial intelligence) algorithms have contributed to the large part of modern advances in AI technologies, huge amount of database for algorithm development and test plays a great role as well. As the performance of object recognition algorithms in still images are surpassing human's ability, research interests shifting to semantic understanding of video contents. This paper proposes candidates of visual verb requiring in the construction of ActionNet as a learning and test database for video understanding. In order to this, we first investigate verb taxonomy in linguistics, and then propose candidates of visual verb from video description database and frequency of verbs. Based on the derived visual verb candidates, we have defined and constructed ActionNet schema and database. According to expanding usability of ActionNet database on open environment, we expect to contribute in the development of video understanding technologies.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.21 no.6
• /
• pp.183-190
• /
• 2011

In this paper, we propose a prototype system for abnormal sound detection and identification which detects and recognizes the abnormal situations by means of analyzing audio information coming in real time from CCTV cameras under surveillance environment. The proposed system is composed of two layers: The first layer is an one-class support vector machine, i.e., support vector data description (SVDD) that performs rapid detection of abnormal situations and alerts to the manager. The second layer classifies the detected abnormal sound into predefined class such as 'gun', 'scream', 'siren', 'crash', 'bomb' via a sparse representation classifier (SRC) to cope with emergency situations. The proposed system is designed in a hierarchical manner via a mixture of SVDD and SRC, which has desired characteristics as follows: 1) By fast detecting abnormal sound using SVDD trained with only normal sound, it does not perform the unnecessary classification for normal sound. 2) It ensures a reliable system performance via a SRC that has been successfully applied in the field of face recognition. 3) With the intrinsic incremental learning capability of SRC, it can actively adapt itself to the change of a sound database. The experimental results with the qualitative analysis illustrate the efficiency of the proposed method.