• Journal of Dental Rehabilitation and Applied Science
• /
• v.27 no.3
• /
• pp.337-342
• /
• 2011

Congenital or traumatic loss on the oral and maxillary area or the loss of jaws due to the surgical excision of a tumor causes functional problems, such as masticatory and swallowing disorders, phonetic problems and psychological disorders in patients. In most cases, a prosthetic restoration is needed to resolve these problems and restore the damaged tissue and function. When loss occurs on the maxilla, foods and liquids leak into the nasal cavity, and a nasal sound can be heard due to air leakage into the removed area. In these cases, the palatal obturator can be used to improve the esthetic and functional aspects because it restores the removed area of the maxilla and closes the opened route between the oral cavity and maxillary sinus or nasal cavity. In this case report, a palatal obturator was applied to patients who had a hemimaxillectomy due to the occurrence of squamous cell carcinoma on the right maxillary area. Therefore, fundamental functions, such as phonetic and swallowing functions were restored, and the esthetic aspects of the facial profile were improved.

• The Journal of the Korea Contents Association
• /
• v.20 no.3
• /
• pp.440-451
• /
• 2020

The purpose of this study is to present a method of Korean speaking activity utilizing mobile learning. It can compensate for the shortcomings of Korean speaking classes. Currently, speaking classes in the Korean as a foreign language site are difficult to interact individually and immediately because there are one professor and several learners. So it is hard for learners to improve their speaking ability in the actual class. However, it is helpful for learners to receive instant and individual feedback and check their pronunciation, intonation and speed. by using mobile learning. Therefore, This study consists of main-activity that can correct their pronunciation, post-activity that can make free dialogues through communication between learner and learner. So learners can improve their pronunciation accuracy and fluency as well as composition of conversation. This activity was applied to the actual class and after that, the satisfaction and opinions of learners were investigated. The results showed that many learners responded positively, but also suggested that they need to supplement mobile-learning activities in classrooms and future APP developments.

• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.4
• /
• pp.9-16
• /
• 2020

Pronunciation recognition systems that use only video information and ignore voice information can be applied to various customized services. In this paper, we develop a system that applies a Bayesian classifier to distinguish Korean vowels via lip shapes in images. We extract feature vectors from the lip shapes of facial images and apply them to the designed machine learning model. Our experiments show that the system's recognition rate is 94% for the pronunciation of 'A', and the system's average recognition rate is approximately 84%, which is higher than that of the CNN tested for comparison. Our results show that our Bayesian classification method with feature values from lip region landmarks is efficient on a small training set. Therefore, it can be used for application development on limited hardware such as mobile devices.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.10
• /
• pp.1-7
• /
• 2021

Recently, since most of the research on correcting speech recognition errors is based on English, there is not enough research on Korean speech recognition. Compared to English speech recognition, however, Korean speech recognition has many errors due to the linguistic characteristics of Korean language, such as Korean Fortis and Korean Liaison, thus research on Korean speech recognition is needed. Furthermore, earlier works primarily focused on editorial distance algorithms and syllable restoration rules, making it difficult to correct the error types of Korean Fortis and Korean Liaison. In this paper, we propose a context-sensitive post-processing model of speech recognition using a LSTM-based sequence-to-sequence model and Bahdanau attention mechanism to correct Korean speech recognition errors caused by the pronunciation. Experiments showed that by using the model, the speech recognition performance was improved from 64% to 77% for Fortis, 74% to 90% for Liaison, and from 69% to 84% for average recognition than before. Based on the results, it seems possible to apply the proposed model to real-world applications based on speech recognition.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.5
• /
• pp.555-567
• /
• 2019

Speech recognition rate is lowered even in a noisy environment, and it is difficult for a person with a speech disability or an inconvenient language to use it in a social life. In addition to improving the inconvenience of using the language, 280 words were selected using the word selection method which was improved when the word was selected considering the pronunciation characteristics of the language impaired. The MEMS development device used in the experiment was made considering material, lead wire type, length and direction. We improved the speech recognition rate by using the developed word selection method and the MEMS device developed to improve the speech recognition rate due to incorrect pronunciation and severe noise. The new method of selecting words and the mems device were improved and the results were included.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.11
• /
• pp.1397-1406
• /
• 2019

In everyday mobile phone calls between the disabled and non-disabled people due to neurological impairment, the communication accuracy is often hindered by combining the accuracy of pronunciation due to the neurological impairment and the pronunciation features of the disabled. In order to improve this problem, the limiting method is MEMS (micro electro mechanical systems), which includes an induction line that artificially corrects difficult vocalization according to the oral characteristics of the language impaired by improving the word of out of vocabulary. mechanical System) Microphone device improvement. S/W improvement is decision tree with invert function, and improved matrix-vector rnn method is proposed considering continuous word characteristics. Considering the characteristics of H/W and S/W, a similar dictionary was created, contributing to the improvement of speech intelligibility for smooth communication.

• The Journal of the Korea Contents Association
• /
• v.6 no.12
• /
• pp.186-191
• /
• 2006

The perception of English labial consonants was investigated via experiment where 40 Korean EFL learners identified nonwords with the target labial consonants [p, b, f, v] in 4 different prosodic locations: initial onset position, intervocalic position before stress, intervocalic position after stress, and final coda position. The overall result showed that the proportion of perception accuracy of the target consonants was rather low, amounting to only 55%. There was also a positional effect since the accuracy rates for perceiving the four target consonants differed by position. Specifically, the average accuracy rate of the target consonant identification was higher in intervocalic position before stress (70%) and initial onset position (67%) than in intervocalic position after stress (45%) and final coda position (36%). Further, the accuracy rate for [f] is was high in all prosodic locations except intervocalic position after stress. The perception patterns were accounted for by the markedness and perceptual factors in conjunction with stress location.

• Journal of Korea Entertainment Industry Association
• /
• v.13 no.4
• /
• pp.17-26
• /
• 2019

In order to study the role of legato to singers in vocal music performance, this paper adopts the methods of demonstration and induction and comparison to analyze the three factors affecting the creation of legato in performance and propose solutions. When thinking about the influence of singing skills on legato, singers will be able to solve such issues as breathing, articulation and vocal register, thus improving their singing skills. When thinking about the influence of singing language on legato, singers will make an in-depth study on the phonetic and structural features of the language to reach legato in language, thus promoting the in-depth study of singers on the singing language. When thinking about the influence of singing emotion on legato, singers will solve the problem of emotional coherence from two aspects of thought and emotion to create legato of emotion, thus promoting the expression of singers' emotion in the work. Obviously, legato plays an important role in improving singers' singing skills, singing language and singing emotion. The aim of the paper is to encourage singers to further deepen their attention to legato in vocal music performance and make better use of legato in singing.

• Journal of Dental Rehabilitation and Applied Science
• /
• v.39 no.4
• /
• pp.229-236
• /
• 2023

Maxillary bone defects may follow surgical treatment of benign and malignant tumors, trauma, and infection. Palatal defects often lead to problems with swallowing and pronunciation from the leakage of air into the nasal cavity and sinus. Obturators have been commonly used to solve these problems, but long-term use of the device may cause irritation of the oral mucosa or damage to the abutment teeth. Utilizing implants in the edentulous area for the fabrication of the obturators has gained attention. This case report describes a patient, who had undergone partial resection of the maxilla due to adenocarcinoma, in need of a new obturator after losing abutment teeth after long-term use of the previous obturator. Implants were placed in strategic locations, and an implant-retained maxillary obturator was fabricated, showing satisfactory results in the rehabilitation of multiple aspects, including palatal defect, masticatory function, swallowing, pronunciation, and aesthetics.

• Journal of the Korea Computer Industry Society
• /
• v.5 no.9
• /
• pp.959-964
• /
• 2004

This study will reilize the learning device of foreign languages using voice recognition that is programmed based on three scenarios by the Conversay SDK. This device is embedd not with basic functions such as pronunciation/phrase recognition function, conversation function etc., but also with additional functions using user's voices such as timer function, alarming function, test function, learning check function etc.