Browse DORAS
Browse Theses
Search
Latest Additions
Creative Commons License
Except where otherwise noted, content on this site is licensed for use under a:

DCU at MediaEval 2011: Rich Speech Retrieval (RSR)

Eskevich, Maria and Jones, Gareth J.F. (2011) DCU at MediaEval 2011: Rich Speech Retrieval (RSR). In: MediaEval 2011 Multimedia Benchmark Workshop, 1-2 Sept 2011, Pisa, Italy.

Full text available as:

[img]
Preview
PDF (DCU submission to MediaEval Rich Speech Retrieval task) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
122Kb

Abstract

We describe our runs and results for the Rich Speech Re- trieval (RSR) Task at MediaEval 2011. Our runs examine the use of alternative segmentation methods on the provided ASR transcripts to locate the beginning of the topic, assum- ing that this will capture or get close to the starting point of the relevant segment; combination of various types of queries and weighting of metadata to move the relevant segment higher in the ranked list; and dierent ASR transcripts to compare the in uence of the ASR transcripts quality. Our results show that newer versions of the transcripts and use of metadata produce better results on average. So far we have not used information about the illocutionary act type corresponding to each query, but analysis of the retrieval results shows dierence in behaviour for queries associated with certatin classes of act.

Item Type:Conference or Workshop Item (Paper)
Event Type:Workshop
Refereed:Yes
Uncontrolled Keywords:Speech search; information retrieval; automatic speech recognition
Subjects:Computer Science > Multimedia systems
Computer Science > Information retrieval
DCU Faculties and Centres:Research Initiatives and Centres > Centre for Digital Video Processing (CDVP)
Research Initiatives and Centres > Centre for Next Generation Localisation (CNGL)
DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Published in:Working Notes Proceedings of the MediaEval 2011 Workshop. Vol-807 . CEUR Workshop Proceedings.
Publisher:CEUR Workshop Proceedings
Official URL:http://ceur-ws.org/Vol-807/
Copyright Information:Copyright is held by the author/owner
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:Science Foundation Ireland
ID Code:16892
Deposited On:16 Apr 2012 11:09 by Gareth Jones. Last Modified 16 Apr 2012 11:09

Download statistics

Archive Staff Only: edit this record