Morphosyntactic Processing of N-Best Lists for Improved Recognition and Confidence Measure Computation - INRIA - Institut National de Recherche en Informatique et en Automatique Accéder directement au contenu
Communication Dans Un Congrès Année : 2007

Morphosyntactic Processing of N-Best Lists for Improved Recognition and Confidence Measure Computation

Stéphane Huet
Guillaume Gravier
Pascale Sébillot

Résumé

We study the use of morphosyntactic knowledge to process N-best lists. We propose a new score function that combines the parts of speech (POS), language model, and acoustic scores at the sentence level. Experimental results, obtained for French broadcast news transcription, show a significant improvement of the word error rate with various decoding criteria commonly used in speech recognition. Interestingly, we observed more grammatical transcriptions, which translates into a better sentence error rate. Finally, we show that POS knowledge also improves posterior based confidence measures.
Fichier principal
Vignette du fichier
IS07.pdf (107.24 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02021878 , version 1 (16-02-2019)

Identifiants

  • HAL Id : hal-02021878 , version 1

Citer

Stéphane Huet, Guillaume Gravier, Pascale Sébillot. Morphosyntactic Processing of N-Best Lists for Improved Recognition and Confidence Measure Computation. 8th Annual Conference of the International Speech Communication Association (Interspeech), 2007, Antwerp, Belgium. pp.1741-1744. ⟨hal-02021878⟩
56 Consultations
66 Téléchargements

Partager

Gmail Facebook X LinkedIn More