تقرير
OLISIA: a Cascade System for Spoken Dialogue State Tracking
العنوان: | OLISIA: a Cascade System for Spoken Dialogue State Tracking |
---|---|
المؤلفون: | Jacqmin, Léo, Druart, Lucas, Estève, Yannick, Favre, Benoît, Rojas-Barahona, Lina Maria, Vielzeuf, Valentin |
سنة النشر: | 2023 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Computer Science - Sound |
الوصف: | 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. |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2304.11073 |
رقم الأكسشن: | edsarx.2304.11073 |
قاعدة البيانات: | arXiv |
كن أول من يترك تعليقا!