paper-with-me

홈 › Papers

OLISIA: a Cascade System for Spoken Dialogue State Tracking

2023-04-20 · Léo Jacqmin, Lucas Druart, Yannick Estève, Benoît Favre, Lina Maria Rojas-Barahona, Valentin Vielzeuf

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.

📄 PDF Abstract BibTeX arXiv:2304.11073

Code (1)

orange-opensource/olisia-dstc11 공식 구현 pytorch

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Data AugmentationDialogue State Trackingspeech-recognitionSpeech RecognitionSpoken Dialogue Systems

Methods 이 논문이 사용한 방법론

DST Dynamic sparse training methods train neural networks in a sparse manner, starting with an initial sparse mask, and periodically updating the mask based on some criteria.

Similar Papers 제목 키워드 기반

Are cascade dialogue state tracking models speaking out of turn in spoken dialogues?

2023-11-03 · Lucas Druart, Léo Jacqmin, Benoît Favre, Lina Maria Rojas-Barahona 외

In Task-Oriented Dialogue (TOD) systems, correctly updating the system's understanding of the user's needs is key to a smooth interaction. Traditionally TOD systems are composed of several modules that interact with one …

Dialogue State Tracking

WavChat: A Survey of Spoken Dialogue Models

2024-11-15 · Shengpeng Ji, Yifu Chen, Minghui Fang, Jialong Zuo 외

Recent advancements in spoken dialogue models, exemplified by systems like GPT-4o, have captured significant attention in the speech domain. Compared to traditional three-tier cascaded spoken dialogue models that compris…

speech-recognitionSpeech RecognitionSpoken Dialogue SystemsSurvey+2

Motion-Omni: End-to-End Joint Speech and Full-Body Motion for Spoken Dialogue

2026-08-28 · Chengqian Ma, Wei Tao, Haoyu Zhang, Yiwen Guo hf

An avatar that holds a conversation should decide what to say and to move while saying it, yet these abilities live in separate model families: spoken dialogue models produce speech without motion, and co-speech motion m…

Is one brick enough to break the wall of spoken dialogue state tracking?

2023-11-03 · Lucas Druart, Valentin Vielzeuf, Yannick Estève

In Task-Oriented Dialogue (TOD) systems, correctly updating the system's understanding of the user's requests (\textit{a.k.a} dialogue state tracking) is key to a smooth interaction. Traditionally, TOD systems perform th…

Dialogue State Tracking

ESPnet-SDS: Unified Toolkit and Demo for Spoken Dialogue Systems

2025-03-11 · Siddhant Arora, Yifan Peng, Jiatong Shi, Jinchuan Tian 외

Advancements in audio foundation models (FMs) have fueled interest in end-to-end (E2E) spoken dialogue systems, but different web interfaces for each system makes it challenging to compare and contrast them effectively. …

DiversitySpoken Dialogue Systems