The LIMSI SDR System for TREC-8.
Jean‐Luc Gauvain, Lori F Lamel, Claude Barras, Gilles Adda, Yannick de Kercadio · 1999
In this paper we report on our TREC-8 SDR system, which combines an adapted version of the LIMSI 1998 Hub-4E transcription system for speech recognition with an IR system based on the Okapi term weighting function. Experimental results are given in terms of word error rate and average precision for both the SDR'98 and SDR'99 data sets. In addition to the Okapi approach, we also investiged a Markovian approach, which although not used in the TREC-8 evaluation, yields comparable results. The evaluation system obtained an average precision of 0.5411 on the reference transcriptions and of 0.5072 on the automatic transcriptions. The word error rate measured on a 10 hour subset is of 21.5%. INTRODUCTION There expansion of different media sources for information dissemination (radio, television, internet) has led to a need for automatic processing tools. Todays methods for audio segmentation, transcription and indexation are manual, with humans reading, listening and watching, annotating to...