OLISIA: a Cascade System for Spoken Dialogue State Tracking - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

OLISIA: a Cascade System for Spoken Dialogue State Tracking

Léo Jacqmin
  • Fonction : Auteur correspondant
  • PersonId : 1144745

Connectez-vous pour contacter l'auteur
Yannick Estève
Benoît Favre
Lina Maria Rojas-Barahona
Valentin Vielzeuf
  • Fonction : Auteur
  • PersonId : 1016921

Résumé

Though Dialogue State Tracking (DST) is a core component of spoken dialogue systems, recent work on this task mostly deals with chat corpora, disregarding the discrepancies between spoken and written language. In this paper, we propose OLISIA, a cascade system which integrates an Automatic Speech Recognition (ASR) model and a DST model. We introduce several adaptations in the ASR and DST modules to improve integration and robustness to spoken conversations. With these adaptations, our system ranked first in DSTC11 Track 3, a benchmark to evaluate spoken DST. We conduct an in-depth analysis of the results and find that normalizing the ASR outputs and adapting the DST inputs through data augmentation, along with increasing the pre-trained models size all play an important role in reducing the performance discrepancy between written and spoken conversations.
Fichier principal
Vignette du fichier
main.pdf (2.08 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04072601 , version 1 (18-04-2023)
hal-04072601 , version 2 (30-08-2023)

Identifiants

Citer

Léo Jacqmin, Lucas Druart, Yannick Estève, Benoît Favre, Lina Maria Rojas-Barahona, et al.. OLISIA: a Cascade System for Spoken Dialogue State Tracking. 2023. ⟨hal-04072601v2⟩
77 Consultations
49 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More