Almost every shot change detection algorithm detects abrupt transition (hard cut) without difficulty, but gradual transitions such as fades, dissolves, wipes are left as hard-to-detect problems. Dissolve effect, among the various gradual transition effects, is one of the most frequently used shot transition methods with special semantic meaning such as scene transition. Information of the shot change type can also be the basis for the shot clustering algorithms. In this paper, we present a fast and effective dissolve-transition detection algorithm based on the spatio-temporal distribution of the macro block pipes in MPEG-compressed video. In the proposed algorithm, the ratio of forward macro blocks in the B-type frames and the spatial distribution of forward/backward macro blocks are utilized for detecting dissolve transition. After finding such sequence of frames, we apply 2 heuristic rules: (1) The global color distributions of the frames at which dissolve starts and terminates are very different, and (2) The duration of dissolve transition is typically more than 0.3 second.

This paper describes preliminary results of automatic recognition of Korean broadcast-news speech. We have been working on flexible vocabulary isolated-word speech recognition, and the same HMM models are used for broadcast-news continuous speech recognition. The recognizer is trained by using phonetically balanced isolated words speech, rather than the broadcast news speech itself. In this research, we use several different lexica to investigate the recognition performance according to the length of the words. We also propose a long-distance bigram language model, which can be used at the first stage of the search, so that it can reduce the recognition errors caused by earlier pruning of correct hypothesis. 1.