• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.1
• /
• pp.77-92
• /
• 2020

When automatic speech recognition (ASR) is provided as a cloud service, it is easy to collect voice and application domain data from users. Harnessing these data will facilitate the provision of more personalized services. In this paper, we demonstrate our transfer learning-based knowledge service that built with the user-generated data collected through our novel system that deliveries personalized ASR service. First, we discuss the motivation, challenges, and prospects of building up such a knowledge-based service-oriented system. Second, we present a Quadruple Transfer Learning (QTL) method that can learn a classification model from a source domain and transfer it to a target domain. Third, we provide an overview architecture of our novel system that collects voice data from mobile users, labels the data via crowdsourcing, utilises these collected user-generated data to train different machine learning models, and delivers the personalised real-time cloud services. Finally, we use the E-Book data collected from our system to train classification models and apply them in the smart TV domain, and the experimental results show that our QTL method is effective in two classification tasks, which confirms that the knowledge transfer provides a value-added service for the upper-layer mobile applications in different domains.

• The Journal of the Korea Contents Association
• /
• v.11 no.9
• /
• pp.429-436
• /
• 2011

There have been several studies reporting that vocal misuse and abuse causes voice problems, as well as laryngeal disease such as laryngitis, vocal nodules, vocal polyp. But few researches have investigated amounts or rates of vocal misuse or vocal abuse of patients. Therefore, the author of this study developed measuring device for vocal misuse and abuse behaviors and compared frequency of vocal misuse and abuse behaviors of normal children and children with vocal nodules. The subjects of this study were five normal children and five children with vocal nodules who were male, lower graders of elementary schools(first to third graders). Based on the results of this study, the frequency of the children with vocal nodules in vocal misuse and abuse using was 5,411(${\pm}145$) and that of the normal children was 3,133(${\pm}257$). The frequency of vocal misuse and abuse behaviors of the children with vocal nodules was around 1.5 time significantly higher than that of normal children(p<.001).

• Journal of Music and Human Behavior
• /
• v.9 no.2
• /
• pp.19-34
• /
• 2012

The purpose of this study was to investigate the empirical elements of non-Korean traditional musicians in the process of Pansori music listening. 5 non-Korean traditional musicians who are not professionally trained Korean music were participated in this study. The data were collected in depth interviews and analyzed from modified ground theory method. The findings showed that the elements of performer's voice, Chang-bub, contents, Gosu's buk sound and Gosu's role evoked various physical, emotional reponses and thoughts in all listeners. Through these responses the listeners awared internal issues related to inner problems and positive intervention aroused inner feelings. Also, emotional responses and awareness were reorganized their negative emotion and resolved through the different dimension of Pansori music.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.45 no.2
• /
• pp.111-118
• /
• 2008

In this paper a novel medium access control mechanism is investigated as a means to support real-time services. The primary goal is to provide constant-bit-rate voice call services to pairs of autonomous mobile nodes operating in ad hoc networks. Here, a time-slot reservation based MAC is considered to provide real-time voice calls and a new MAC called the time-slot reservation coordination function(TRCF) is presented. In addition to this isochronous type MAC protocol development, the proposed protocol is modeled using a Markov chain in order to predict its behavior. The performance of TRCF is analytically derived and the performance measures such as average wait time taken for a call connection and throughput are obtained.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.4
• /
• pp.221-228
• /
• 2023

Physical and mental changes caused by emotions can affect various behaviors, such as driving or learning behavior. Therefore, recognizing these emotions is a very important task because it can be used in various industries, such as recognizing and controlling dangerous emotions while driving. In this paper, we attempted to solve the emotion recognition task by implementing a multimodal model that recognizes emotions using both audio and video data from different domains. After extracting voice from video data using RAVDESS data, features of voice data are extracted through a model using 2D-CNN. In addition, the video data features are extracted using a slowfast feature extractor. And the information contained in the audio and video data, which have different domains, are combined into one feature that contains all the information. Afterwards, emotion recognition is performed using the combined features. Lastly, we evaluate the conventional methods that how to combine results from models and how to vote two model's results and a method of unifying the domain through feature extraction, then combining the features and performing classification using a classifier.

• The Journal of Society for e-Business Studies
• /
• v.22 no.4
• /
• pp.141-158
• /
• 2017

Along with IT development, customers are getting more easily to express their opinions using various IT channels. In this situation, complaint management is a pressing issue for companies to acquire and maintain loyal customers with low cost. Most of previous studies have investigated customer complaint information by quantitative variables such as demographic information, transaction information, or complaint frequency, but studies focusing on qualitative aspects of complaint information are limited. Therefore, this paper considers the possibility for customers to leave even when they complain occasionally or briefly. This paper analyzes the quantitive aspects as well as the qualitative aspects using sentiment analysis with Exit-voice theory. The dataset contains 268,364 inquiries of 46,235 customers obtained from a contact center of a private security company in Korea. This paper carries out logistic regression and the results imply that the customers's explicit response and their implicit sentiment have different effect on customers leave. This study is expected to provide useful suggestions for the effective complaint management.

• The KIPS Transactions:PartD
• /
• v.11D no.2
• /
• pp.443-452
• /
• 2004

The paper presents an intelligent space management system for ubiquitous computing. The system is basically a home/office automation system that could control light, electronic key, and home appliances such as TV and audio. On top of these basic capabilities, there are four elegant features in the system. First, we can access the system using either a cellular Phone or using a browser on the PC connected to the Internet, so that we control the system at any time and any place. Second, to provide more human-oriented interface, we integrate voice recognition functionalities into the system. Third, the system supports not only reactive services but also proactive services, based on the regularities of user behavior. Finally, by exploiting embedded technologies, the system could be run on the hardware that has less-processing power and storage. We have implemented the system on the embedded board consisting of StrongARM CPU with 205MHz, 32MB SDRAM, 16MB NOR-type flash memory, and Relay box. Under these hardware platforms, software components such as embedded Linux, HTK voice recognition tools, GoAhead Web Server, and GPIO driver are cooperated to support user-friendly intelligent space.

• Journal of Korea Entertainment Industry Association
• /
• v.13 no.8
• /
• pp.167-180
• /
• 2019

The purpose of this study is to find out the results of synesthesia speech training using similar language for shaping audiobook text. The audiobook text for training uses Tolstoy's work, and uses similar language of tone, tone, pose, speed, intonation, accent, and expression of emotions. The participants who ten visually impaired trainee in H library were selected for qualitative research. Based on the research questions raised in this study, the results are as follows. First, synesthesia training, in which more than two senses of the five senses work simultaneously in voice training for audio book text shaping, produced the result by visualizing the original purpose, meaning, and background of the text. Second, the use of similar language was helpful in the whole process of expressing the meaning of sentence and dialogue for audiobook text shaping. In addition, although there were some differences among the study subjects, they found commonalities that considered tone, pose, and intonation important. Third, the visually impaired have advanced sensory aspects and memory, which resulted in rapid acquisition of metabolism and acceptance of transmission during training. In addition, the teacher's friendly behavior was a very important key mediator in the training process.

• Cross-Cultural Studies
• /
• v.39
• /
• pp.309-328
• /
• 2015

This study is a consideration of Xu Xiao-Bin(徐小斌)'s Sounds of nature(天?) in the mutual text point of view of Lee Cheong-jun's Sopyonje series. Xu Xiao-Bin's Sounds of nature shows similar motive to Lee Cheong-jun's Sopyonje series that is a story of a mother who damages her daughter's eyes and the daughter. however, it is accepted in totally different ways that the action of father/mother who damage their daughter's eyes. the mother in Sounds of nature is a composer as well as singer and the father in Sopyonje is a singer. The mother's behavior is not able to have duty in Sounds of nature due to it is focused in 'mother's action' rather than a singer but the father's behavior is focused in 'singer's action' in Sopyonje. therefore the action of the father, who is a singer, is considered not merely personal desire of father but also desire to preserve 'singing' as a national culture in public status. the length between two novels are clear in the two daughter's point of views. the daughter in "Sounds of nature" refuses her destiny made from her mother. The daughter's behavior of recovering her own volition, becomes frankly showing the falsehood of 'mother's love. In comparison, the daughter's voice is under the shade in Sopyonje. she surrenders herself to the fate made by her father, and she does not show her desire. This is the point that the difference is created by gender of writers.

• Journal of Korean Academy of Nursing
• /
• v.53 no.5
• /
• pp.538-555
• /
• 2023

Purpose: This qualitative study used interpretative phenomenological analysis and photovoice methods to explore the meaning of non-suicidal self-injury experienced by adolescents. Methods: Participants were adolescents enrolled in middle and high schools in Gyeonggi-do and Jeollabuk-do who were selected through snowball sampling. Six participants had repeatedly engaged in self-injurious behavior for over a year. Data were collected through in-depth interviews and the photovoice method between November 2020 and July 2021. The collected data were analyzed using six steps of interpretative phenomenological analysis. Results: The results yielded 5 main themes and 18 subthemes. The main themes were 'a silent cry to an indifferent world', 'a heartache that one endures with scars', 'an inescapable cycle', 'filling the space in one's heart', and 'healing the wounds'. The study findings revealed that the self-injurious behavior of adolescents began as a consequence of feeling lost and struggling with conflicts at home and school, which helped them relieve tension and pain. Nonetheless, inflicting self-injury only left signs of regret and remorse, which became a trace that the participants wanted to hide. However, the wounds healed after receiving attention and support from others. They were determined to stop engaging in repeated self-injurious behaviors and made efforts to do so. Conclusion: This study can be used as a basis for the development of educational programs to prevent non-suicidal self-injury in adolescents. Additionally, it can inform nursing interventions that focus on building support systems to help adolescents who attempt self-injury.