The Spoken Web Search Task

Abstract

In this paper, we describe the “Spoken Web Search” Task, which
\nis being held as part of the 2012 MediaEval campaign. The
\npurpose of this task is to perform audio search in multiple
\nlanguages, with very little resources being available for each
\nindividual language. The data is being taken from audio content
\nthat was created in live and realistic low-resource settings.