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.
@article{arxiv.2304.11073,
title = {OLISIA: a Cascade System for Spoken Dialogue State Tracking},
author = {Léo Jacqmin and Lucas Druart and Yannick Estève and Benoît Favre and Lina Maria Rojas-Barahona and Valentin Vielzeuf},
journal= {arXiv preprint arXiv:2304.11073},
year = {2023}
}