Abstract | ||
---|---|---|
Soundtracks of videos contain a rich source of content-based information. In this paper, we propose an audio-based approach to video indexing and handling. Audio data is analysed by means of frequency analysis, and music and voice are independently detected even if they occur together. The method is implemented on a system called Video in Time as an example of creating reasonable condensed versions of dramas or movies by excerpting meaningful video segments. Users can select the desired replaying time from several different levels, depending on how much time can be afforded for viewing. Detection rates for music and voice are evaluated and experiences with the system are mentioned |
Year | DOI | Venue |
---|---|---|
1997 | 10.1109/MMCS.1997.609596 | Ottawa, Ont. |
Keywords | Field | DocType |
network utilization,inherent burstiness,traffic smoothing,vbr video transmission,vbr video,enhanced video handling,smoothing method,audio analysis,connection cost,speech processing,layout,frequency analysis,image segmentation,telephony,drama,feature extraction,data analysis,data mining,music,indexing,voice,telegraphy,motion pictures,movies | Video capture,Computer science,Multiview Video Coding,Artificial intelligence,Smacker video,Video compression picture types,Computer vision,Video processing,Audio mining,Speech recognition,Video tracking,Audio analyzer,Multimedia | Conference |
ISBN | Citations | PageRank |
0-8186-7819-4 | 5 | 1.08 |
References | Authors | |
16 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kenichi Minami | 1 | 43 | 5.71 |
Akihito Akutsu | 2 | 308 | 77.61 |
Hiroshi Hamada | 3 | 7 | 1.44 |
Yoshinobu Tonomura | 4 | 554 | 149.46 |