• MALSORI
• /
• no.50
• /
• pp.71-83
• /
• 2004

Recently, broadcast news speech recognition has become one of the most attractive research areas. If we can transcribe automatically the broadcast news and store their contents in the text form instead of the video or audio signal itself, it will be much easier for us to search for the multimedia databases to obtain what we need. However, the desirable speech signal in the broadcast news are usually affected by the interfering signals such as the background noise and/or the music. Also, the speech of the reporter who is speaking over the telephone or with the ill-conditioned microphone is severely distorted by the channel effect. The interfered or distorted speech may be the main reason for the poor performance in the broadcast news speech recognition. In this paper, we investigated some methods to cope with the problems and we could see some performance improvements in the noisy broadcast news speech recognition.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.967-970
• /
• 2005

The Music Player MAF Player Format of ISO/IEC 23000-2 FDIS consists of MP3 data, MPEG-7 metadata and one optional JPEG image data based on MPEG-4 File Format. However, the current Music Player MAF format does not allow multiple JPEG image data or timed text data. It is helpful to use timed text data and multiple JPEG images in the various multimedia applications. For example, listening material for the foreign language needs an additional book which has text and images, the audio contents which can get image and text data can be helpful to understand the whole story and situations well. In this paper, we propose the detailed file structure in conjunction with MPEG-4 File Format in order to improve the functionalities, which carry multiple image data and text data with synchronization information between MP3 data and other resources.

• Journal of Korea Multimedia Society
• /
• v.18 no.8
• /
• pp.988-995
• /
• 2015

In 2013, Academy Award for Best Animated Short Film was granted to Walt Disney's short animation, (2012). With various aspects of its excellence, I focus on the very effective use of digital lightings and underscores for storytelling as its success factors. In this respect, this paper aims at analyzing the roles of the visual factors, especially tone, contrast, etc. created by lightings, and audio factors, especially underscores, in the film's story development. I find that can be characterized by the well-built story structure with distinct three acts. The main stream of the story is expressed with the overall mood that is created by the fine adjustments of brightness of the main light, and contrast. And the direction and the intensity of the lighting successfully describe the emotions of the characters in each scene. In addition, I find that properly chosen and positioned underscores make the development of the story more dynamic and more harmonized.

• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.147-150
• /
• 2004

허밍에 의한 고정도의 오디오 정보 검색 시스템을 구현하기 위해서는 시스템 측에서 발생 가능한 문제점과 유저 측에서 발생 가능한 문제점을 함께 고려한 해결 기법이 요구된다. 유저 측에서는 허밍시 자신의 애매한 기억에 기인한 음표의 삽입이나 탈락과 같은 가창실수, 허밍 도중에 음정 및 박자의 불안정한 변화, 같은 곡을 노래 부를지라도 개인차에 의해 상이한 음정과 템포 등이 발생한다. 또한 시스템 측에서 발생 가능한 사항으로써, 비록 허밍질의가 완벽하더라도 입력 허밍 신호를 멜로디 매칭에 이용되는 정확한 특징량의 추출 및 음악 표기로의 변환이 어렵다는 점이다. 종래의 오디오 정보 검색 시스템에서는 이러한 문제점을 해결하기 위해 다양한 멜로디 표현법과 매칭 방법이 제안되고 있으나, 성능 면에서는 아직 만족할 만한 결과를 얻지 못하고 있다. 따라서 이러한 문제점들을 해결하기 위해서 본 논문에서는 허밍 멜로디의 효과적인 표현방법과 시스템 및 유저 측에서 발생 가능한 오류에 강건한 멜로디 매칭 방법을 제안한다.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2000.04a
• /
• pp.120-125
• /
• 2000

We propose a semi-automatic and dynamic indexing algorithm for multi-media database(e.g. movie files, audio files), which are difficult to create indexes expressing their emotional or abstract contents, according to user's sensitivity by using user's histories of access to database. In this algorithm, we simply categorize data at first, create a vector space of each user's interest(user model) from the history of which categories the data belong to, and create vector space of each data(title model) from the history of which users the data had been accessed from. By continuing the above method, we could create suitable indexes, which show emotional content of each data. In this paper, we define the recurrence formulas based on the proposed algorithm. We also show the effectiveness of the algorithm by simulation result.

• 한국정보통신설비학회:학술대회논문집
• /
• 2004.08a
• /
• pp.81-85
• /
• 2004

내용기반 질의법 (Content-based Query Method)은 멀티미디어 데이터가 가지고 있는 고유의 특성을 검색의 단서로 하여 질의하는 방법이다. 따라서 이러한 내용 기반의 디지털 오디오 콘텐츠 시스템은 유저가 데이터베이스 내에서 찾고자 하는 오디오 관련 정보의 질의 방법으로써 그 노래의 멜로디 정보를 입력함으로써 이루어지게 된다. 본 논문에서는 가수명이나 노래 제목, 혹은 가사의 일부 등 기존의 음악 검색에 필수적인 텍스트 정보인 키워드를 전혀 모르는 상태에서, 휴대폰이나 컴퓨터의 마이크를 통해 자신이 기억하고 있는 노래의 일부분을 흥얼거리는 것만으로, 각종 오디오 정보를 손쉽게 찾아주는 내용기반 질의법을 이용한 디지털오디오 검색시스템 (MuseFinder)을 소개한다. 또한 실제 유저의 편이성을 고려한 GUI에 기초한 고성능의 검색시스템을 구현하는데 있어 주요 이슈와 고려사항에 대해서 살펴보고 그 해결 방법을 제안한다.

• Journal of the Korean Institute of Educational Facilities
• /
• v.5 no.3
• /
• pp.107-115
• /
• 1998

Open education is more relevant to the current educational reality which requires the liberalization, individualization and creativeness, and the effectiveness of open education will be maximized with the full utilization of instructional media. As well known, there are many different types of instructional media to promote open education such as print material, audio material, still picture, movie, computer, and multimedia. The main criteria to choose effective instructional media for open education depend upon easiness of supply and retrieval of information, and promotion of more frequent interaction among participants. In addition, utilization method, cost, curriculum contents, as well as school culture are also elements to consider in the selection of right instructional media.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.131-132
• /
• 2008

It is necessary to develop a high-speed wireless transmission system, which is able to send medical informations to the emergency medical center during emergency patient transportation. In this research, a system which transmits patient’s vital signs and a real-time audio/video contents of the event has been designed, developed, and the suitability of the system has been verified. Test results indicate that the system is capable of transmitting vital signal data, including 17 numeric data, 12 waveforms and 113 events, reading the affected part by forwarding a $320{\times}240$ pixel image at 2fps. Also, the full-duplex voice transmission of the system at 8bit/64kbps is enough to make stable communication between emergency medical technicians and hospital professionals possible. After numerous hours of driving, the packet loss of patient vital signs is 0.013%.

• Proceedings of the KIEE Conference
• /
• 1999.11b
• /
• pp.216-218
• /
• 1999

This paper presents an advanced virtual lecture system for power system which is based on web. So far, conventional web-based virtual lecture systems which simply would use hyper-text couldn't use characteristics of multimedia in web. Comparing with printed publication, such conventional virtual lecture systems as only display on monitor couldn't be superior in validity and effectiveness. So, in this paper the proposed virtual lecture system uses web-based multimedia functions, including lecture-note and AOD(Audio on Demand), in order to overcome an individual difference of learning efficiency and suggests simple simulation programs for lecture contents which can be performed directly in on-line.

• Proceedings of the KAIS Fall Conference
• /
• 2006.05a
• /
• pp.558-560
• /
• 2006

웹 콘텐츠의 특성상 분배, 복제 및 조작이 용이하기 때문에 원 정보의 저작권 침해로 인한 재산권 침해 피해가 나날이 증가하고 있어, 막대한 비용이 투자된 웹 콘텐츠의 무단도용을 방지하고 분쟁 발생시 소유권에 대한 분쟁을 해결하기 위한 노력이 계속되고 있다. 본 논문에서는 웹 콘텐츠의 소유권 및 저작권 보호를 위한 오디오 콘텐츠에 대한 워터마크 생성, 삽입 및 검출, 검증 시스템을 설계 및 구현한다. 본 시스템은 저작권 보호에 대한 전문지식이 없는 일반관리자도 용이하게 이용할 수 있는 사용자 인터페이스를 갖추고 있으며, 이러한 디지털 오디오 워터마킹의 적용을 통한 소유권 및 저작권 보호는 궁극적으로 콘텐츠 제작 의뢰자로 하여금 제작 의지를 강화하여 제작 의뢰 건수를 증가시킬 수 있을 것으로 기대되어 문화콘텐츠 등의 디지털 콘텐츠 제작업체의 매출 신장에 도움을 주게될 것이다.