Paper Info
Title
Towards automatic speaker retrieval for large multimedia archives
Abstract
In this paper we discuss the challenges of scaling a speaker retrieval system for small audiovisual collections towards a speaker retrieval system for large audio (visual) archives. We show that with our large scale speaker diarization approach it is possible to perform query-by-example speaker retrieval; to search for audiovisual documents in which a particular person is talking. On a selection of the ICSI meeting corpus we obtain a Mean Average Precision of 0.49 and precision-at-ten of 0.70. On a much larger archive of three months of Dutch broadcast television we obtain a precision-at-ten of 0.52.
Year
DOI
Venue
2010
10.1145/1877850.1877857
Proceedings of the 3rd international workshop on Automated information extraction in media production
Keywords
DocType
Citations 
large multimedia archives,large scale speaker diarization,large audio,speaker tracking,speaker retrieval,speaker retrieval system,audiovisual document,speaker diarization,towards automatic speaker retrieval,query-by-example speaker retrieval,icsi meeting corpus,large scale diarization,mean average precision,small audiovisual collection,dutch broadcast television,larger archive,query by example
Conference
2
PageRank 
References 
Authors
0.49
7
2
Name
Order
Citations
PageRank
Marijn Huijbregts116414.92
David van Leeuwen2447.06