• 한국멀티미디어학회지
• /
• 제5권3호
• /
• pp.5-15
• /
• 2001

No Abstract (See Full-text)

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2013년도 추계학술대회
• /
• pp.507-509
• /
• 2013

본 논문에서는 최근 많은 관심을 받고 있는 안드로이드를 활용한 경증 자폐성장애인을 위한 보완대체의사소통 지원프로그램을 구현하였다. 보완대체의사소통이란 구어 및 비구어적 의사표현하기 어려운 사람들을 위해 사용하는 의사소통체계로서, 본 프로그램에서는 자폐장애인의 의사소통과 의사소통 언어의 선택적 빈도를 측정하는 방법과 자폐 아등의 지적 장애인의 언어에 대한 기본적인 훈련을 하는 방법을 소개한다. 본 논문에서는 보완대체 의사소통에서의 언어표상기법을 활용하여 여러 의사소통의 자유가 없는 사용자들이 효과적인 의사소통 및 학습을 할 수 있도록 개발하였으며, TTS(Text to Speech)를 사용하여 사용자의 의사를 육성으로 전달할 수 있도록 하였다. 그림판기능을 제공하여 사용자의 의사전달의 폭을 넓히고 언어빈도 측정을 통한 사용자의 언어사용빈도 그리고 자폐아의 경우 의식적 무의식 의사전달에 따른 백분율 수치를 두어 도움을 주도록 구현하였다.

• 대한임베디드공학회논문지
• /
• 제17권6호
• /
• pp.347-353
• /
• 2022

In this paper, we propose a method that performs a text-video retrieval model by replacing video properties using captions. In general, the exisiting embedding-based models consist of both joint embedding space construction and the CNN-based video encoding process, which requires a lot of computation in the training as well as the inference process. To overcome this problem, we introduce a video-captioning module to replace the visual property of video with captions generated by the video-captioning module. To be specific, we adopt the caption generator that converts candidate videos into captions in the inference process, thereby enabling direct comparison between the text given as a query and candidate videos without joint embedding space. Through the experiment, the proposed model successfully reduces the amount of computation and inference time by skipping the visual processing process and joint embedding space construction on two benchmark dataset, MSR-VTT and VATEX.

• 한국정보통신학회논문지
• /
• 제25권11호
• /
• pp.1486-1494
• /
• 2021

문자 인식은 스마트 주차, text to speech 등 최근 다양한 플랫폼에서 필요로 하는 기술로써, 기존의 방법과 달리 새로운 시도를 통하여 그 성능을 향상시키려는 연구들이 진행되고 있다. 그러나 문자 인식에 사용되는 이미지의 품질이 낮을 경우, 문자 인식기 학습용 이미지와 테스트 이미지간에 해상도 차이가 발생하여 정확도가 떨어지는 문제가 발생된다. 이를 해결하기 위해 본 논문은 문자 인식 모델 성능이 다양한 품질 데이터에 대하여 강인하도록 이미지 초해상도 및 문자 인식을 결합한 통째학습 신경망을 설계하고, 대안적 통째학습 알고리즘을 구현하여 통째 신경망 학습을 수행하였다. 다양한 문자 이미지 중 차량 번호판 이미지를 이용하여 대안적 통째학습 및 인식 성능 테스트를 진행하였고, 이를 통해 제안하는 알고리즘의 효과를 검증하였다.

• 한국의류학회지
• /
• 제39권5호
• /
• pp.703-713
• /
• 2015

Consumers' psychological demands for e-tail shopping have increased as websites have become one of the most dominant retail outlets for various fashion products. The lack of realistic social stimuli in virtual contexts (websites) has been a major limitation for many online shoppers. Prior research has focused on the viable role of technology to improve positive social factors in e-tailing; however, this study tests the role of tone in text in fashion e-tail sites on consumers' trust and choice confidence. We conducted a self-administered online survey with 309 individuals from the U.S.. The results indicated positive effects of casual tone in text-based content of a fashion e-tail site on trust and confidence. Trust also has a significant positive effect on confidence. Both trust and confidence improved purchase intention. Given the high price of employing an avatar or simulated salesperson online, using tone in text to increase positive social effect on shoppers can be a positive alternative when managers plan e-tail strategies contributing to consumers' positive shopping experience online. Discussions and study limitations are provided.

• 한국의류학회지
• /
• 제44권2호
• /
• pp.295-309
• /
• 2020

In 2019, Japan announced trade regulations against Korean products; consequently, the sales of Japanese products in Korea dropped due to a Korean consumers' boycott. This study measured the Korean consumers' political consumption behavior toward Japanese fashion products. Unstructured text data from online media sources and consumer posted sources such as blog and SNS were collected. Text mining techniques and semantic network analysis were used to process unstructured data. This study used text mining techniques and semantic network analysis to process data. The results identified boycotting Japanese fashion products and buycotting alternative products and Korean brands due to consumers' political consumption. Two brand cases were investigated in detail. Online text data before and after the political action were compared and significant changes in consumption as well as emotional expressions were identified. Product related industry sectors were identified in terms of the political consumption of fashion: liquor, automobile and tourism industry sectors were closely linked to the fashion sector in terms of boycotting. More "boycott" and "buycott" fashion brands (reflected in consumer attitudes and feelings) were detected in consumer driven texts than in media driven sources.

• 컴퓨터교육학회논문지
• /
• 제5권4호
• /
• pp.111-121
• /
• 2002

컴퓨터와 네트워크의 급속한 발달로 인터넷 사용자가 급증하면서 모든 분야에서 정보전달 매체로서 웹의 활용이 보편화되고 있다. 교육적인 측면에서도 기존의 교실에서의 수업이나 인쇄매체를 통한 교육의 대체매체로서 웹의 활용에 대한 관심이 증대하고 있다. 본 연구에서는 7차 고등학교 수학과 교육과정에서 독자적인 영역으로 새로 분리된 '확률과 통계' 영역에 대해 웹상에서 활용가능한 교육용 전자교재의 구현사례를 제시한다. 확률의 계산이나 통계치의 계산 등과 같은 수리연산보다는 응용학문으로서의 확률과 통계의 개념과 원리의 이해에 중점을 두어 개발하였다.

• 영어어문교육
• /
• 제12권2호
• /
• pp.1-18
• /
• 2006

This study investigates the types of interactional modifications employed by Japanese and Korean university students during text-based chats. In particular, this study focuses on the role of a network-based medium on the use of interactional modifications, which have been claimed to facilitate interlanguage development. The results show that students use a variety of features of interactional modifications. The most used strategies were the use of paralinguistic features, framing, overt indication of understanding/agreement, and clarification checks, which reveals inconsistent results with findings from research on the negotiation of meaning in face-to-face interaction. Results suggest that the computer-mediated communication (CMC) environment requires the above mentioned strategies and students are able to adapt to this new context by employing alternative strategies. The majority of negotiations were generated by content and lexical items either to resolve communication problems or to better manage interactions, and very few negotiations occurred in terms of grammar. The findings suggest that text-based synchronous chats can be an effective tool for promoting interactive competence, but their effectiveness on grammatical development is uncertain.

• 대한음성학회지:말소리
• /
• 제47호
• /
• pp.131-140
• /
• 2003

We propose a new method of generating client models for HMM based text-dependent speaker verification system with only a small amount of training data. To make a client model, statistical methods such as segmental K-means algorithm are widely used, but they do not guarantee the quality or reliability of a model when only limited data are avaliable. In this paper, we propose a blind speech segmentation based on level building DTW algorithm as an alternative method to make a client model with limited data. In addition, considering the fact that voiced sounds have much more speaker-specific information than unvoiced sounds and energy of the former is higher than that of the latter, we also propose a new score evaluation method using the observation probability raised to the power of weighting factor estimated from the normalized log energy. Our experiment shows that the proposed methods are superior to conventional HMM based speaker verification system.

• 한국동물학회:학술대회논문집
• /
• 한국동물학회 1998년도 한국생물과학협회 학술발표대회
• /
• pp.97-97
• /
• 1998

No Abstract, See Full Text