• The Journal of the Acoustical Society of Korea
• /
• v.40 no.5
• /
• pp.530-536
• /
• 2021

Recently, due to the development of deep learning, end-to-end speech recognition, which directly maps graphemes to speech signals, shows good performance. Especially, among the end-to-end models, conformer shows the best performance. However end-to-end models only focuses on the probability of which grapheme will appear at the time. The decoding process uses a greedy search or beam search. This decoding method is easily affected by the final probability output by the model. In addition, the end-to-end models cannot use external pronunciation and language information due to structual problem. Therefore, in this paper conformer with lexicon transducer is proposed. We compare phoneme-based model with lexicon transducer and grapheme-based model with beam search. Test set is consist of words that do not appear in training data. The grapheme-based conformer with beam search shows 3.8 % of CER. The phoneme-based conformer with lexicon transducer shows 3.4 % of CER.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.9 no.9
• /
• pp.1-16
• /
• 2019

This study was carried out to develop a physics education program for foreign students of university in Korea to improve their ability to major in the field and to prevent them from becoming dropout. The subjects of the study are five Chinese students attending a natural science and engineering college. Prior to the development of the physics education program, the researchers developed basic physics textbooks for the foreign students and questionaries for diagnosis and summative evaluation, and utilized them to apply a total of seven classes. After the application of the classes, the results of the student's diagnosis and summative evaluation, the teacher's diaries, the observer's diaries, and the transcripts were analyzed by triangulation method. In addition, Nvivo12 was used for the analysis of the teacher's and observer's diaries to help with qualitative analysis. The results of the study are as follows: First, the oder and contents of physics education program for students of the natural science and engineering college were presented in detail, and basic physics textbooks and tools for diagnosis and summative assessment were developed. Second, as a result of the analysis of the diagnosis and summative assessment results of the program, the students' basic physics achievement improved by an average of 40 points due to the application of the developed program. Third, as a result of the application of the program using Nvivo12, meaningful node and actual cases were extracted. There were 10 types of nodes created such as understanding of the students, teaching method, rate of the participation, level differences, language problems, relevance to majors, curriculum and methods of education in the country of origin, cooperative learning, and interest inducement. The researcher provided suggestions on physics education methods for students of science and engineering colleges in Korea based on the related cases.

• Journal of Music and Human Behavior
• /
• v.18 no.2
• /
• pp.45-66
• /
• 2021

This study aimed to develop a group rap making program and examine its applicability to improve communication skills of adolescents with mild intellectual disabilities (ID). Three adolescents with ID participated in a total of six 50-minute group sessions over 4 weeks. The group rap making program included three stages: understanding the context of communication, learning how to communicate with others, and applying the communicative behaviors in a group setting. To examine changes in the participants' communication skills, the rap lyrics constructed by participants were analyzed and communicative behaviors were observed during sessions and analyzed in terms of asking questions and providing information to others. Also, a social communication skills checklist was rated by the participant's caregivers. The analysis of rap lyrics showed that the expressions included in the rap were diversified as the session proceeded. Changes in observed behaviors supported that participants became to engage in communication with others more actively in order to complete the group rap. While the social communication skills checklist tended to increase, there was a difference in degree of change depending on the level of language communication skills. These results indicate that a group rap making can be an effective option for these adolescents to learn how to communicate with their peers, which presents implications for how rap making can be used for therapeutic purpose with more diversified population.

• Journal of Digital Convergence
• /
• v.17 no.6
• /
• pp.1-9
• /
• 2019

In an effort to explore the effects of Youtube video-watching activities on Korean college students' English reading comprehension skills, 148 undergraduate students who enrolled in a General English class at a university in Korea participated in the present study. Participants were randomly classified into four groups - three experimental groups and one control group - according to when they watch videos: before class (n = 33), during class (n = 42), after class (n = 36), and none (n = 37). Over 16 weeks, the three experimental groups engaged in Youtube video-watching activities for about 10 minutes before, during, and after the class, while the control group did not. Pre- and post-tests were administered to confirm the effects of the use of Youtube videos on improving English reading comprehension skills. To compare the improvement between groups, a one-way ANOVA was also run. Major findings are as follows: First, participants in all the three experimental groups significantly improved their English reading comprehension skills, indicating the beneficial effects of Youtube video-watching activities. However, there was no statistically significant difference in the mean improvement between the groups. Based on this, limitations and suggestions for the future research are discussed at the end.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.2
• /
• pp.750-762
• /
• 2019

The importance of the call center as a contact point for the enterprise is growing. However, call centers have difficulty with their operating agents due to the agents' lack of knowledge and owing to frequent agent turnover due to downturns in the business, which causes deterioration in the quality of customer service. Therefore, through an N-bank call center case study, we developed a system to reduce the burden of keeping up business knowledge and to improve customer service quality. It is a "real-time agent advisor" system that provides agents with answers to customer questions in real time by combining AI technology for speech recognition, natural language processing, and questions & answers for existing call center information systems, such as a private branch exchange (PBX) and computer telephony integration (CTI). As a result of the case study, we confirmed that the speech recognition system for real-time call analysis and the corpus construction method improves the natural speech processing performance of the query response system. Especially with name entity recognition (NER), the accuracy of the corpus learning improved by 31%. Also, after applying the agent advisor system, the positive feedback rate of agents about the answers from the agent advisor was 93.1%, which proved the system is helpful to the agents.

• Phonetics and Speech Sciences
• /
• v.13 no.2
• /
• pp.57-66
• /
• 2021

This study focuses on the issue of automatic severity classification of dysarthric speakers based on speech intelligibility. Speech intelligibility is a complex measure that is affected by the features of multiple speech dimensions. However, most previous studies are restricted to using features from a single speech dimension. To effectively capture the characteristics of the speech disorder, we extracted features of multiple speech dimensions: voice quality, prosody, and pronunciation. Voice quality consists of jitter, shimmer, Harmonic to Noise Ratio (HNR), number of voice breaks, and degree of voice breaks. Prosody includes speech rate (total duration, speech duration, speaking rate, articulation rate), pitch (F0 mean/std/min/max/med/25quartile/75 quartile), and rhythm (%V, deltas, Varcos, rPVIs, nPVIs). Pronunciation contains Percentage of Correct Phonemes (Percentage of Correct Consonants/Vowels/Total phonemes) and degree of vowel distortion (Vowel Space Area, Formant Centralized Ratio, Vowel Articulatory Index, F2-Ratio). Experiments were conducted using various feature combinations. The experimental results indicate that using features from all three speech dimensions gives the best result, with a 80.15 F1-score, compared to using features from just one or two speech dimensions. The result implies voice quality, prosody, and pronunciation features should all be considered in automatic severity classification of dysarthria.

• The Journal of the Korea Contents Association
• /
• v.21 no.6
• /
• pp.791-803
• /
• 2021

To improve the oral health level of North Korean defectors, it is necessary to improve awareness of oral health care along with treatment of oral diseases. The purpose of this study is to develop an oral health education program that can be applied to North Korean defectors who have settled in local communities. To develop the program, three steps were taken: literature review, in-depth interview with experts, and program development applying the Dick&Carey model. As a result of in-depth expert interviews, what should be considered in oral health education for North Korean defectors is the need to understand North Korean defectors in advance, to familiarize themselves with the daily language of North Korea, to develop a synchronization strategy suitable for North Korean defectors, and to connect with whole body health. It was found that there was a need to establish the contents of education and to seek realistic education methods that reflect the characteristics of local communities. As a result of developing the program, fifty learning goals were developed, and ten sessions were planned. The oral health education program for North Korean defectors developed in this study will be of practical help to dental hygienists planning oral health education for North Korean defectors in the future and North Korean defectors.

• Journal of the Korean Society for Library and Information Science
• /
• v.55 no.1
• /
• pp.393-413
• /
• 2021

Digital humanities, which creates new and innovative knowledge through the combination of digital information technology and humanities research problems, can be seen as a representative multidisciplinary field of study. To investigate the intellectual structure of the digital humanities field, a network analysis of authors and keywords co-word was performed on a total of 441 papers in the last two years (2019, 2020) at the Digital Humanities Conference. As the results of the author and keyword analysis show, we can find out the active activities of Europe, North America, and Japanese and Chinese authors in East Asia. Through the co-author network, 11 dis-connected sub-networks are identified, which can be seen as a result of closed co-authoring activities. Through keyword analysis, 16 sub-subject areas are identified, which are machine learning, pedagogy, metadata, topic modeling, stylometry, cultural heritage, network, digital archive, natural language processing, digital library, twitter, drama, big data, neural network, virtual reality, and ethics. This results imply that a diver variety of digital information technologies are playing a major role in the digital humanities. In addition, keywords with high frequency can be classified into humanities-based keywords, digital information technology-based keywords, and convergence keywords. The dynamics of the growth and development of digital humanities can represented in these combinations of keywords.

• Journal of the Korea Convergence Society
• /
• v.12 no.8
• /
• pp.1-11
• /
• 2021

The purpose of this study was to analyze the trends and characteristics of 'stress urinary incontinence' research through word frequency analysis, and their relationships were modeled using word embedding. Abstract data of 9,868 papers containing abstracts in PubMed's MEDLINE were extracted using a Python program. Then, through frequency analysis, 10 keywords were selected according to the high frequency. The similarity of words related to keywords was analyzed by Word2Vec machine learning algorithm. The locations and distances of words were visualized using the t-SNE technique, and the groups were classified and analyzed. The number of studies related to stress urinary incontinence has increased rapidly since the 1980s. The keywords used most frequently in the abstract of the paper were 'woman', 'urethra', and 'surgery'. Through Word2Vec modeling, words such as 'female', 'urge', and 'symptom' were among the words that showed the highest relevance to the keywords in the study on stress urinary incontinence. In addition, through the t-SNE technique, keywords and related words could be classified into three groups focusing on symptoms, anatomical characteristics, and surgical interventions of stress urinary incontinence. This study is the first to examine trends in stress urinary incontinence-related studies using the keyword frequency analysis and word embedding of the abstract. The results of this study can be used as a basis for future researchers to select the subject and direction of the research field related to stress urinary incontinence.

• Journal of the Korean Society for information Management
• /
• v.38 no.2
• /
• pp.1-18
• /
• 2021

An academic library is one of the largest information sources for international students to obtain learning resources, which have a great impact on their studies. However, most academic libraries currently have not provided adequate multilingual services except English, which makes it difficult for international students whose mother language is not English to perform academic work. Accordingly, the present study defines the customized services for international students as the ones that have been supported in ltiple languages among academic library services and aims to examine their effect on user satisfaction in academic libraries. Furthermore, the study has compared international students' satisfaction with academic libraries - one that provides appropriate customized services with the other that does not. The surveys have been conducted with Chinese international students in two different universities and a total of 138 responses were analyzed. The study found that the customized services for the international students influenced their satisfaction with library use. In particular, multilingual services had positive effects on satisfaction with services such as brochures/signs, access to and use of resources through the homepage, and user instruction. The findings of the study suggest practical insights on how academic libraries provide effective services for supporting international students' academic tasks.