Summary: | 碩士 === 國立暨南國際大學 === 資訊工程學系 === 94 === In this thesis, a Web-based English learning system using news video materials has been proposed. We believe that the anchorperson’ or reporters’ speech and text of news video are helpful for non-native users to learn English. In order to add more value of the learning materials, we choose the news video which was reported with video text in English. Generally, when both speech and video text are in the same language, the video text is usually called “closed-captions”. To facilitate the accessibility of the closed-captions, we use video text extraction technique to extract the closed-captions and to locate the position of words. The extracted closed-captions provide important clues for cross-media access, and the located words benefit the looking up vocabulary in an online dictionary. The information we discovered from the news video helps us to design a feasible application that helps learners to improve their listening and reading abilities.
|