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 Huijbregts | 1 | 164 | 14.92 |
David van Leeuwen | 2 | 44 | 7.06 |