NWU Institutional Repository

The spoken web search task at MediaEval 2011

dc.contributor.authorMetze, Florian
dc.contributor.authorRajput, Nitendra
dc.contributor.authorAnguera, Xavier
dc.contributor.authorDavel, Marelie H.
dc.contributor.authorGravier, Guillaume
dc.contributor.authorVan Heerden, Charl
dc.contributor.authorMantena, Gautam
dc.contributor.authorMuscariello, Armando
dc.contributor.authorPrahallad, Kishore
dc.contributor.authorSzoke, Igor
dc.contributor.authorTejedor, Javier
dc.date.accessioned2019-02-01T13:52:33Z
dc.date.available2019-02-01T13:52:33Z
dc.date.issued2012-03
dc.description.abstractIn this paper, we describe the "Spoken Web Search" Task, which was held as part of the 2011 MediaEval benchmark campaign. The purpose of this task was to perform audio search with audio input in five languages, with very little resources being available in each language. The data was taken from "spoken web" material collected over a mobile phone connection by IBM India. We present results from several ndependent systems, developed by five teams and using different approaches, compare and fuseen_US
dc.identifier.citationMetze, F. et al. The spoken web search task at MediaEval 2011, in Proc. Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), pp 5165-5168, Kyoto, Japan, March 2012.en_US
dc.identifier.urihttp://hdl.handle.net/10394/31784
dc.language.isoenen_US
dc.publisherAcoustics, Speech and Signal Processing (ICASSP)en_US
dc.subjectlow-resource speech recognitionen_US
dc.subjectevaluationen_US
dc.subjectspoken weben_US
dc.subjectaudio searchen_US
dc.subjectspoken term detectionen_US
dc.titleThe spoken web search task at MediaEval 2011en_US
dc.typeArticleen_US

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
metze-2012-medieval (1).pdf
Size:
134.51 KB
Format:
Adobe Portable Document Format
Description:
metze-2012-medieval 2011

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.61 KB
Format:
Item-specific license agreed upon to submission
Description: