• 한국음향학회:학술대회논문집
• /
• 한국음향학회 2002년도 하계학술발표대회 논문집 제21권 1호
• /
• pp.87-90
• /
• 2002

This paper analyzes statistically the relationship between size and balance of text corpus by evaluation of the effect of interview sentences in language model for Korean broadcast news transcription system. Our Korean broadcast news transcription system's ultimate purpose is to recognize not interview speech, but the anchor's and reporter's speech in broadcast news show. But the gathered text corpus for constructing language model consists of interview sentences a portion of the whole, $15\%$ approximately. The characteristic of interview sentence is different from the anchor's and the reporter's in one thing or another. Therefore it disturbs the anchor and reporter oriented language modeling. In this paper, we evaluate the effect of interview sentences in language model for Korean broadcast news transcription system and analyze statistically the relationship between size and balance of text corpus by making an experiment as the same procedure according to varying the size of corpus.

• 한국ITS학회 논문지
• /
• 제8권5호
• /
• pp.128-137
• /
• 2009

본 연구는 현재 지상파 DMB의 방송자막에 대한 사용자들의 인식을 파악하여, 향후 방송자막 디자인 개선 방향을 제시하고자 하였다. 먼저 방송자막에 대한 기존 연구들을 고찰하였다. 그 결과 프로그램 시청 시 방송자막이 중요한 역할을 하며, 글자 수의 최소화, 명료성을 높이는 글자체와 색상의 배열, 구성 요소의 재배치가 방송자막의 가독성을 높이는 주요 요소로 파악되었다. 그러나 실제 지상파 DMB 사용자들을 대상으로 설문 조사를 한 결과 화질, 화면 구성, 색상 및 명암 등에서 긍정적인 평가가 낮았다. 또한 방송자막의 가독성, 정보의 전달, 자막 구성, 글자체, 글자 수 및 글자 크기 등의 평가에서는 더욱 부정적인 것으로 나타났다. 앞으로 방송자막 형태 및 구성, 정보량의 제한, 글자의 선명성 및 크기, 색상 배치 및 선명성 등에서 지상파 DMB 화면에 적합하고, 사용자의 편이성을 고려한 자막 디자인의 개발이 절실히 요청된다.

• International journal of advanced smart convergence
• /
• 제13권1호
• /
• pp.12-22
• /
• 2024

Software applications have a huge and inseparable impact on our lives. The complexity of the applications increases rapidly to support high performance and multifunction. Accordingly, the cost model for applications is increasingly important. Line of Code (LOC) and Man-Month (M/M) as the cost model measure the quantitative sides of the applications. Unlike them, Function Point (FP) measures the functionalities of the application. FP is efficient for estimating qualitative characteristics, but it is restricted to measuring the cost of an application using the wireless data broadcast which can support any number of clients. In this paper, we propose, a Function Point model for Information services using wireles data Broadcast (FPIB) to measure the development cost of an application that serves using the wireless data broadcast environment. FPIB adopts critical parameters of the wireless broadcast environment and the complexity of them to measure effectively the cost developing the application. Through the evaluation comparing the proposed FPIB with FP, we reveal the effectiveness of the proposed FPIB.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 1999년도 KOBA 방송기술 워크샵 KOBA Broadcasting Technology Workshop
• /
• pp.35.2-42
• /
• 1999

When we see a binary black and white image, it appears. to our visual sense, to become clearer because of a pseudo halftone. This is because when we don't notice of all the details of the image, instead we see from a more global standpoint. We presented a theory and experimental results for layered model which extended external world, retina and brain of the two dimensional visual model. This paper propose the objective evaluation to coincide with the subjective evaluation of the human in ordered to evaluate the relative merits of the various modulation method. We obtain experimentally the restored images and the measure of approximation of the density four division and ordered dither method. The measure of approximation present s the objective evaluation scale to coincide with the subjective evaluation of the two modulation images.

• The Journal of the Acoustical Society of Korea
• /
• 제26권3E호
• /
• pp.74-79
• /
• 2007

In this paper, we report our recent work on a indexing and retrieval system of broadcast news using audio content analysis. Key issues addressed in this work are two major parts of the audio indexing system: anchorperson detection based on audio segmentation, and phone-based spoken document retrieval, developed in the framework of the emerging MPEG-7 standard. Experiments are conducted on a database of Britisch broadcast news videos. We discuss the development of the retrieval system, and the evaluation of each part and the retrieval system.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2021년도 하계학술대회
• /
• pp.260-263
• /
• 2021

3GPP (3rd generation partnership project)는 5G 요구 조건을 충족시키기 위해 release 16 에서 FeMBMS (further evolved MBMS)를 LTE 기반 5G MBMS 로 개선하였다. 이어서, 현재 개발 중인 release 17 에서 NR 기반의 디지털 방송을 위한 NR MBS (multimedia broadcast services)가 논의되고 있다. 본 논문에서는 LTE (long term evolution) 기반 5G MBMS (fifth generation multimedia broadcast & multicast services)와 5G NR (fifth generation new radio)의 PBCH (physical broadcast channel) 에 대한 송수신기 구조를 설명하고, 성능을 평가한다. 본 논문에서는 가산 백색 가우시안 잡음(additive white Gaussian noise: AWGN) 및 고정 환경 하에서 LTE 기반 5G MBMS 와 5G NR 에 대한 PBCH 의 성능을 비교한다.

• 정보처리학회논문지C
• /
• 제12C권2호
• /
• pp.243-250
• /
• 2005

낮은 대역폭이나 잦은 단절 같은 무선 통신의 근본적인 제약으로 인한 방송 시스템의 성능 저하를 완화할 수 있는 방법 중의 하나는 클라이언트에 캐시를 도입하는 것이다. 본 논문에서는 비트 벡터를 이용한 혼합 데이터 방송 시스템에서 클라이언트가 최근에 요구하는 데이터를 효과적으로 방송할 수 있도록 pull 기반 방송전략을 제안한다. 그리고, 방송 알고리즘의 특성을 고려한 효율적인 캐싱 전략을 제안하고 시스템의 성능을 평가한다. 평가 결과에 따르면, 제안한 전략들을 수용한 시스템이 응답 시간 측면에서 전반적으로 좋은 성능을 보여준다.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2010년도 하계학술대회
• /
• pp.346-348
• /
• 2010

In this paper, we propose the IPTV QoE evaluation method reflecting service user's preference. This method can evaluate the IPTV service QoE using the fuzzy integral because it usefully employs a subjective decision for QoE(Quality of Experience) evaluation. IPTV subscribers can prepare a criterion to select an IPTV provider who provides high qualityQoE.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.76-79
• /
• 2009

This paper investigates the performance of a vehicular rear-view camera through quantifying the image quality based on several objective criteria from the ISO (International Organization for Standardization). In addition, various experimental environments are defined considering the conditions under which a rear-view camera may need to operate. The process for evaluating the performance of a rear-view camera is composed of five objective criteria: noise test, resolution test, OECF (opto-electronic conversion function) test, color characterization test, and pincushion and barrel distortion tests. The proposed image quality quantification method then expresses the results of each test as a single value, allowing easy evaluation. In experiments, the performance evaluation results are analyzed and compared with those for a regular digital camera.

• 방송공학회논문지
• /
• 제10권2호
• /
• pp.149-155
• /
• 2005

We have proposed an objective evaluation method using ESNR as the measure of approximation by the visual model, which coincides with MOS, a subjective evaluation method. For two-value images, we have used five kinds of modulation methods: 1) ordered dither, 2) least mean error, 3) pulse density low division, 4) simple two-value, and 5) random dither methods. The purpose of this paper is to investigate the validity of ESNR, by comparing the proposed method together with the existing representative methods such as PSNR and WSNR, with the subjective method MOS. The results of a series of experiments show that the ranking by MOS coincides with ESNR, though does not coincides with PSNR and WSNR.