Title :
Speaker dependent video indexing based on audio-visual interaction
Author :
Tsekeridou, S. ; Pitas, I.
Author_Institution :
Dept. of Inf., Thessaloniki Univ., Greece
Abstract :
A content-based video indexing method is presented that aims at temporally indexing a video sequence according to the actual speaker. This is achieved by the integration of audio and visual information. Audio analysis leads to the extraction of a speaker identity label versus time diagram. Visual analysis includes scene cut detection, face shot determination, mouth region extraction and tracking and finally talking face shot determination. Results from both sources are combined to improve speaker dependent video indexing. Such a task enables flexible video retrieval or browsing in cases where queries according to speaker identities are imposed. Speaker recognition errors are reduced to 2%
Keywords :
audio signal processing; audio-visual systems; content-based retrieval; database indexing; feature extraction; speaker recognition; video databases; video signal processing; audio analysis; audio information; audio-visual interaction; content-based video indexing method; face shot determination; mouth region extraction; mouth region tracking; scene cut detection; speaker dependent video indexing; speaker identities; speaker identity label extraction; speaker recognition errors reduction; talking face shot determination; time diagram; video browsing; video retrieval; video sequence; visual analysis; visual information; Cepstral analysis; Face detection; Indexing; Informatics; Layout; Linear predictive coding; Performance analysis; Speaker recognition; Speech analysis; Video sequences;
Conference_Titel :
Image Processing, 1998. ICIP 98. Proceedings. 1998 International Conference on
Print_ISBN :
0-8186-8821-1
DOI :
10.1109/ICIP.1998.723498
