• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.267-269
• /
• 2020

입모양 인식(Lip Reading) 기술은 입술 움직임을 통해 발화를 분석하는 기술이다. 본 논문에서는 일상적으로 사용하는 10개의 상용구에 대해서 발화자의 안면 움직임 분석을 통해 실시간으로 분류하는 연구를 진행하였다. 시간상의 연속된 순서를 가진 영상 데이터의 특징을 고려하여 3차원 합성곱 신경망 (Convolutional Neural Network)을 사용하여 진행하였지만, 실시간 시스템 구현을 위해 연산량 감소가 필요했다. 이를 해결하기 위해 차 영상을 이용한 2차원 합성곱 신경망과 LSTM 순환 신경망 (Long Short-Term Memory) 결합 모델을 설계하였고, 해당 모델을 이용하여 실시간 시스템 구현에 성공하였다.

• Annual Conference on Human and Language Technology
• /
• 2006.10e
• /
• pp.65-70
• /
• 2006

본 논문에서는 EPG 정보 검색을 위한 자연어 대화 시스템에 대해 논한다. 자연어 대화 시스템 구축을 위한, 대화 예제를 이용한 상황 기반 대화 관리 방법론은, 효율적이고 실용적인 대화 시스템 구축을 가능하게 한다. 대화 시스템은 사용자 발화에 대해 적합한 시스템응답 발화를 출력하는 과정으로 진행되며, 이를 위해, 사용자 발화 의미 분석, 대화 관리, 시스템 응답 발화 생성의 과정을 거친다. 정확하고 신속한 정보의 전달이 중요한 EPG 정보 검색 도메인의 특성상 EPG 데이터베이스의 관리 및 갱신이 중요한 요소로 작용한다. 이를 위해 웹마이닝 기반의 EPG 데이터베이스 관리자를 구현함으로써 데이터베이스 구축에 필요한 비용을 최소화하고, 신속하고 정확한 정보를 제공할 수 있었다.

• The Journal of the Korea Contents Association
• /
• v.20 no.11
• /
• pp.402-410
• /
• 2020

It is very important for Academic purpose Korean leaner to understand main ideas and overall context of texts. In order to understand the overall context and mail ideas of text, learners need output task, ways to perform what they are learning, such as retelling. That would help them to realize that there is a gap between what they have understood and what they can actually speak or write. These out activities help learners comprehend the text more efficiently, while at the same time raising their confidence level. The purpose of this study was to develop an education plan to improve reading comprehension ability by using retelling activity. To achieve the purpose of the study, retelling activity, which makes it easier to take an integrated approach to language function and is considered to be relatively effective, was utilized because of the characteristics of retelling activity education instead of teacher-centered education methods.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.77-85
• /
• 2023

After COVID-19, communication through online platforms has increased, leading to an accumulation of massive amounts of conversational text data. With the growing importance of summarizing this text data to extract meaningful information, there has been active research on deep learning-based abstractive summarization. However, conversational data, compared to structured texts like news articles, often contains missing or transformed information, necessitating consideration from multiple perspectives due to its unique characteristics. In particular, vocabulary omissions and unrelated expressions in the conversation can hinder effective summarization. Therefore, in this study, we restructured by considering the characteristics of Korean conversational data, fine-tuning a pre-trained text summarization model based on KoBART, and improved conversation data summary perfomance through a refining operation to remove redundant elements from the summary. By restructuring the sentences based on the order of utterances and extracting a central speaker, we combined methods to restructure the conversation around them. As a result, there was about a 4 point improvement in the Rouge-1 score. This study has demonstrated the significance of our conversation restructuring approach, which considers the characteristics of dialogue, in enhancing Korean conversation summarization performance.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.13 no.6
• /
• pp.96-105
• /
• 2017

In this paper, we investigated the age classification from the speaker by analyzing the voice calls of the emergency center. We classified the adult and elderly from the call center calls using behavioral speech utterances and SVM(Support Vector Machine) which is a machine learning classifier. We selected two behavioral speech utterances through analysis of the call data from the emergency center: Silent Pause and Turn-taking latency. First, the criteria for age classification selected through analysis based on the behavioral speech utterances of the emergency call center and then it was significant(p <0.05) through statistical analysis. We analyzed 200 datasets (adult: 100, elderly: 100) by the 5 fold cross-validation using the SVM(Support Vector Machine) classifier. As a result, we achieved 70% accuracy using two behavioral speech utterances. It is higher accuracy than one behavioral speech utterance. These results can be suggested age classification as a new method which is used behavioral speech utterances and will be classified by combining acoustic information(MFCC) with new behavioral speech utterances of the real voice data in the further work. Furthermore, it will contribute to the development of the emergency situation judgment system related to the age classification.

• Phonetics and Speech Sciences
• /
• v.16 no.2
• /
• pp.19-27
• /
• 2024

The Lombard effect is an involuntary response to speakers' experiences in the presence of noise during voice communication. This study aimed to investigate the Lombard effect by comparing the acoustic features of children and adults under different listening conditions. Twelve male children (5-9 years old) and 12 young adult men (24-35 years old) were recruited to produce speech under three different listening conditions (quiet, noise-55 dB, noise-70 dB). Acoustic analyses were then carried out to characterize their acoustic features, such as F0, intensity, duration, and vowel space area, under the three listening conditions. A Lombard effect was observed in the intensity and duration for children and adults who participated in this study under adverse listening conditions. However, we did not observe a Lombard effect in the F0 and vowel space areas of either group. These findings suggest that children can adjust their speech production in challenging listening conditions as much as adults.

• Journal of Digital Convergence
• /
• v.20 no.2
• /
• pp.47-56
• /
• 2022

With the advent of online platforms, individuals have been able to trade small resources, such as a room, in the market. However, as there is no clear regulation on these economic activities, various side effects have emerged. Accordingly, the government reestablished related policies to resolve the unintended consequences of these economic activities. However, the policy has not been implemented yet, and many participants do not comply with the policy. Therefore, this study intends to examine their perceptions in detail. For this purpose, a text mining technique was applied. Posts and comments from major online communities were collected. By applying the topic modeling technique, 5 topics were derived. Compliance with the government's policy is a voluntary decision. Therefore, it is necessary to carry out an in-depth understanding of the policy target. Therefore, based on this study, it is expected that in the future, methods to induce them to conform to policy can be discussed in detail.

• Phonetics and Speech Sciences
• /
• v.15 no.3
• /
• pp.27-35
• /
• 2023

This study aimed to investigate the effect of Chinese on the production of Korean rhythm. Korean and Chinese are typologically classified into different rhythmic categories; because of this, the phonological properties of Korean and Chinese are similar and different at the same time. As a result, Chinese can exert both positive and negative influences on the realization of Korean rhythm. To investigate the influence of the rhythm of the native language of L2 learners on their target language, we conducted an acoustic analysis using acoustic metrics like of the speech of 5 Korean native speakers and 10 advanced Chinese Korean learners. The analyzed material is a short paragraph of five sentences containing a variety of syllable structures. The results showed that KS and CS rhythms are similar in %V, VarcoV, and nPVI_S. However, CS, unlike KS, showed characteristics closer to those of a stress-timed language in the values of %V and VarcoV. There was also a significant difference in nPVI_V values. These results demonstrate a negative influence of the native language in the realization of Korean rhythm. This can be attributed to the fact that all vowels in Chinese sentence are not pronounced with the same emphasis due to neutral tone. In this sense, this study allowed us to observe influences of L1 on L2 production of rhythm.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.3
• /
• pp.323-329
• /
• 2014

In spoken language research, transcription process needs to be carried out to translate voice data into text. Transcription tool, support program of transcription, offers various information such as content and time of utterance and speaker information. For this reason, inexperienced computer users are having trouble familiarizing with the program. Moreover, since there are little transcription tools developed domestically in Korea, they are usually not suitable for Korean environment. In this paper, we propose a transcription tool which supports not only Korean transcription but easy-to-use interface environment for novice. The transcription supporting function is also provided to minimize mistake that might happen in the process of transcription. And a system structure will be provided for data reliability. Usability of the proposed tool is evaluated in accordance with transcription experience. The evaluation result shows that transcription process and transcription support function have become faster and more convenient respectively.

• Proceedings of the Korean Institute of Industrial Safety Conference
• /
• 2002.05a
• /
• pp.213-216
• /
• 2002

산소가 없는 상태에서 비교적 낮은 온도에서의 열, 충격 등에 의해 용이하게 발화, 연소하는 불안정한 물질에 의한 사고는 이전부터 많이 알려져 있다. 최근에는 fine chemical 분야의 발전에 따라 그 위험성이 인식되지 않은 채 제조되는 불안정한 물질이 늘고 있다［1-2］.(중략)