• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.11a
• /
• pp.153-155
• /
• 2018

정확한 영상 검색을 지원하기 위해 다양한 데이터와 방법들을 통한 메타데이터 생성 연구들이 이루어지고 있다. 자막 데이터를 기존의 키워드 기반의 메타데이터 생성 방법을 이용했을 경우, 구어체, 불완전 문장의 특징을 가진 특징을 반영하는데 어려움이 있었다. 또한, 단순히 키워드 매칭에 의존하기 때문에 문장에 중의적 단어가 포함되어 있을 경우에 검색 정확도가 떨어진다는 한계점이 있다. 따라서, 본 논문에서는 이러한 문제를 해결하기 위해 문장 전체를 특정 단위로 표현한 메타데이터를 생성한다. 이를 위해 비지도 학습인 RNN-LSTM 기반 네트워크를 이용하여 자막을 인코딩하고 장면 지식으로 생성하는 방법을 제안한다. 실험에서는 본 시스템을 통해 임의의 자막을 입력하고 유사도 기반의 결과 비교를 통해 자막 메타데이터의 정성적 평가를 수행하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.135-136
• /
• 2021

최근 지상파 UHD 방송에서는 자막을 비디오 패킷에 삽입하여 전달하는 기존 방식이 아닌 별도의 전송로로 전달하는 폐쇄형 자막(closed caption) 방식을 적용하고 있다. 또한 자막에는 문자 뿐만 아니라 이미지까지 포함하여 청각장애인의 프로그램 이해도를 높이는데 활용할 수 있다. 따라서 본 논문에서는 청각장애 시청자가 방송 콘텐츠 내용의 이해도를 향상시키기 위하여 지상파 UHD 방송에서 기존의 문자 자막과 움직이는 이미지 자막(=감정표현 자막)을 수신하여 동시에 표현할 수 있는 수신시스템을 제안한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.131-134
• /
• 2021

지상파 방송에서는 청각장애인을 위해 폐쇄자막(closed caption) 서비스가 제공되고 있지만, 이를 저장하여 VOD 서비스 등에 제공하고자 할 때는 영상과의 비동기화(desynchronization) 문제로 인해 활용할 수 없는 문제가 있다. 본 논문에서는 이를 해결하기 위해 자동 음성인식(automatic speech recognition)과, 자막 동기화 문제에 맞게 변경된 동적계획법(modified dynamic programming)을 이용하는 방법을 제안한다. 문자열 정렬에서 삽입과 삭제 등 간격(gap)의 발생을 제어하는 제약조건과 그에 따른 점수 구조를 적용함으로써 문자열 정렬 성능을 개선한다. 또한 정렬된 폐쇄자막과 음성인식 문자열로부터 시간 동기정보를 복원하고 동기화된 자막을 생성하는 방법을 제안한다. 실제 TV 프로그램과 자막에 적용하여 기존 방법에 비해 성능의 향상이 있음을 확인하였다.

• The KIPS Transactions:PartB
• /
• v.9B no.5
• /
• pp.541-548
• /
• 2002

This paper proposes an XML based Multimedia Annotation and Retrieval System, which can represent and retrieve video data efficiently using XML. The system provides a graphical user interface for annotating, searching, and browsing multimedia data. It is Implemented based on the hierarchical metadata model to represent multimedia information. The metadata about video is organized based on multimedia description schema using XML Schema that basically conforms to the MPEG-7 standard. Also, for the effective indexing and retrieval of multimedia data, video segments are annotated and categorized using the closed caption.

• Journal of Korea Game Society
• /
• v.19 no.1
• /
• pp.73-84
• /
• 2019

This study is intended to suggest ways to improve the quality of the service of subtitles provided for the convenience of viewing for deaf people on e-sports broadcast content and game streamer content. Generally, subtitling files of broadcast content are manually written on air by stenographers, so a delay of 3 to 5 seconds is inevitable compared to the original content. Therefore, the present study proposed the formation of an automatic synchronization calibration system using speech recognition technology. In addition, a content application experiment using this system was conducted, and the final result confirmed that the time of synchronization error of subtitling data could be reduced to less than 1 second.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.2
• /
• pp.499-503
• /
• 2024

Broadcasting programs are provided to various media such as Internet replay, OTT, and IPTV services as well as self-broadcasting. In this case, it is very important to provide keywords for search that represent the characteristics of the content well. Broadcasters mainly use the method of manually entering key keywords in the production process and the archive process. This method is insufficient in terms of quantity to secure core metadata, and also reveals limitations in recommending and using content in other media services. This study supports securing a large number of metadata by utilizing closed caption data pre-archived through the DTV closed captioning server developed in EBS. First, core metadata was automatically extracted by applying Google's natural language AI technology. The next step is to propose a method of finding core metadata by reflecting priorities and content characteristics as core research contents. As a technology to obtain differentiated metadata weights, the importance was classified by applying the TF-IDF calculation method. Successful weight data were obtained as a result of the experiment. The string metadata obtained by this study, when combined with future string similarity measurement studies, becomes the basis for securing sophisticated content recommendation metadata from content services provided to other media.

• Journal of Popular Narrative
• /
• v.25 no.4
• /
• pp.263-288
• /
• 2019

Barrier-free films enhance accessibility to audiovisual image contents by providing specific information on screen and through sound so that people with vision or hearing loss can receive the same amount of information as those without disabilities and immerse themselves in the audiovisual images. This study pays attention to barrier-free audiovisual contents in relation to the cultural civil rights of people with vision or hearing loss in South Korea. While institutional efforts have been made in the 2010s to improve the access to audiovisual media of people with vision or hearing loss, the goal of enabling people with vision or hearing loss to fully enjoy all audiovisual contents at a level equal to the non-disabled has not yet been realized. Amid the lingering conflict between disabled groups and multiplexes that has lasted years, the global video streaming service Netflix has aggressively threatened the dominance of local multiplexes with the launch of its Korean service. As Netflix, which is subject to U.S. regulations guaranteeing the rights of people with vision or hearing loss, has produced original dramas and movies involving Korean production teams, the cultural civil rights discourse of the disabled has transitioned to the issue of the rights of cultural consumers crossing national borders in the era of globalization. Changes in the media environment raise the issue of civil rights guarantees in which disabled people enjoy the right to simultaneously watch movies and comment on movies by participating in a common discourse, equally with non-disabled people. The "right to be part of the audience for Korean cinema" for Korean deaf people, which has long been neglected, should also be considered as a cultural civil right that crosses the boundaries of language, nation and disabilities. This essay examines the current issues surrounding the right to cultural entertainment of people with vision or hearing loss in South Korea in conjunction with the contemporary trend of rapid changes in the media environment and the global spread of the movement for cultural civil rights of people with disabilities, and suggests the need for visual culture studies to take a serious step toward disability studies.