Crestani, Fabio 2009 This paper describes a number of experiments that explored the issues surrounding the retrieval of spoken documents. Two such issues were examined. First, attempting to find the best use of speech recogniser output to produce the highest retrieval effectiveness. Second, investigating the potential problems of retrieving from a so-called "mixed collection", i.e. one that contains documents from both a speech recognition system (producing many errors) and from hand transcription (producing presumably near perfect documents). The result of the first part of the work found that merging the transcripts of multiple recognisers showed most promise. The investigation in the second part showed how the term weighting scheme used in a retrieval system was important in determining whether the system was affected detrimentally when retrieving from a mixed collection. application/pdf https://susi.usi.ch/global/documents/318283 https://n2t.net/ark:/12658/srd1318283 https://susi.usi.ch/documents/318283/files/crestani_LNCS_2009_2.pdf eng info:eu-repo/semantics/altIdentifier/ark/12658/srd1318283 info:eu-repo/semantics/openAccess License undefined Lecture notes in computer science. - Springer. - 2009, vol. 1513, p. 397-407 info:eu-repo/classification/udc/004 Mixing and merging for spoken document retrieval http://purl.org/coar/resource_type/c_6501