Overview of the CLEF-2006 cross-language speech retrieval track

  • Authors:

  • Douglas W. Oard;Jianqiang Wang;Gareth J. F. Jones;Ryen W. White;Pavel Pecina;Dagobert Soergel;Xiaoli Huang;Izhak Shafran

  • Affiliations:

  • College of Information Studies and Institute for Advanced Computer Studies, University of Maryland, College Park, MD;Department of Library and Information Studies, State University of New York at Buffalo, Buffalo, NY;School of Computing, Dublin City University, Dublin 9, Ireland;Microsoft Research, Redmond, WA;Microsoft Research, Redmond, WA;MFF UK, Praha 1, Czech Republic;MFF UK, Praha 1, Czech Republic;College of Information Studies, University of Maryland, College Park, MD

  • Venue:
  • CLEF'06 Proceedings of the 7th international conference on Cross-Language Evaluation Forum: evaluation of multilingual and multi-modal information retrieval
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

The CLEF-2006 Cross-Language Speech Retrieval (CL-SR) track included two tasks: to identify topically coherent segments of English interviews in a known-boundary condition, and to identify time stamps marking the beginning of topically relevant passages in Czech interviews in an unknown-boundary condition. Five teams participated in the English evaluation, performing both monolingual and cross-language searches of speech recognition transcripts, automatically generated metadata, and manually generated metadata. Results indicate that the 2006 English evaluation topics are more challenging than those used in 2005, but that cross-language searching continued to pose no unusual challenges when compared with monolingual searches of the same collection. Three teams participated in the monolingual Czech evaluation using a new evaluation measure based on differences between system-suggested and ground truth replay start times, with results that were broadly comparable to those observed for English.