LIUM ASR System for ETAPE French Evaluation Campaign: Experiments on System Combination Using Open-Source Recognizers

Abstract

AbstractIn this paper, we report the LIUM participation in the ETAPE [1] (Évaluations en Traitement Automatique de la Parole) evaluation campaign, on the rich transcription task for French track. After describing the ETAPE goals and guidelines, we present our ASR system, which ranked first in the ETAPE evaluation campaign. Two ASR systems were used for our participation in ETAPE 2011. In addition to the LIUM ASR system based on CMU Sphinx project, we utilized an additional open-source ASR system based on the RASR toolkit. We evaluate, in this paper, the gain obtained with various acoustics modeling and adaptation techniques for each of the two systems, as well as with various system combination techniques. The combination of two different ASR systems allows a significant WER reduction, from 23.6% for the best single ASR system to 22.6% for the combination.Keywordsautomatic speech recognitioncross-system combinationevaluation campaign