HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

System Combination by Driven Decoding

Abstract : 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.
Document type :
Conference papers
Complete list of metadata

Cited literature [10 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01318073
Contributor : Bibliothèque Universitaire Déposants Hal-Avignon Connect in order to contact the contributor
Submitted on : Thursday, November 9, 2017 - 9:24:29 AM
Last modification on : Tuesday, March 22, 2022 - 2:40:01 PM
Long-term archiving on: : Saturday, February 10, 2018 - 12:36:23 PM

File

System_combination_by_driven_d...
Files produced by the author(s)

Identifiers

Collections

Citation

Benjamin Lecouteux, Georges Linarès, Yannick Estève, J. Mauclair. System Combination by Driven Decoding. IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07 , Apr 2007, Honolulu, United States. ⟨10.1109/ICASSP.2007.366919⟩. ⟨hal-01318073⟩

Share

Metrics

Record views

123

Files downloads

73