System Combination by Driven Decoding - Archive ouverte HAL Access content directly
Conference Papers Year : 2007

System Combination by Driven Decoding


The combination of Automatic Speech Recognition (ASR) systems generally relies on a posteriori merge of system outputs or on a cross-adaptation. In this paper, we propose an integrated approach where the search of a primary system is driven by the outputs of a secondary one. This method allows to drive the primary system search by using the one-best hypotheses and the word posteriors gathered from the secondary system. Experiments are carried out within the experimental framework of the ESTER evaluation campaign [1]. Results show that the driven decoding algorithm significantly outper-forms the two single ASR systems (-8% of relative WER,-1.7% absolute). Finally, we investigate the interactions between driven decoding and cross-adaptations. The best cross-adaptation strategy in combination with the driven decoding process brings to a final absolute gain of about 1.9% WER.
Fichier principal
Vignette du fichier
System_combination_by_driven_decoding.pdf (57.85 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01318073 , version 1 (09-11-2017)



Benjamin Lecouteux, Georges Linarès, Yannick Estève, Julie Mauclair. System Combination by Driven Decoding. 32nd International Conference on Acoustics, Speech and Signal Processing - ICASSP 2007, IEEE, Apr 2007, Honolulu, United States. pp.IV-341--IV-344, ⟨10.1109/ICASSP.2007.366919⟩. ⟨hal-01318073⟩
142 View
96 Download



Gmail Facebook X LinkedIn More