A Survey on Spoken Language Understanding: Recent Advances and New Frontiers

TL;DR

The paper addresses the evolving landscape of Spoken Language Understanding (SLU) by synthesizing advances driven by neural models and pretrained language models. It introduces a new taxonomy that contrasts single vs. joint modeling, implicit vs. explicit joint modeling, and pretrained vs. non-pretrained paradigms, and surveys emerging frontiers across contextual, multi-intent, cross-domain, cross-lingual, and low-resource SLU. It highlights practical challenges and proposes an open-source portal with datasets, baselines, and leaderboards to accelerate SLU research. Together, these contributions provide a cohesive, forward-looking reference for researchers and practitioners in SLU.

Abstract

Spoken Language Understanding (SLU) aims to extract the semantics frame of user queries, which is a core component in a task-oriented dialog system. With the burst of deep neural networks and the evolution of pre-trained language models, the research of SLU has obtained significant breakthroughs. However, there remains a lack of a comprehensive survey summarizing existing approaches and recent trends, which motivated the work presented in this article. In this paper, we survey recent advances and new frontiers in SLU. Specifically, we give a thorough review of this research field, covering different aspects including (1) new taxonomy: we provide a new perspective for SLU filed, including single model vs. joint model, implicit joint modeling vs. explicit joint modeling in joint model, non pre-trained paradigm vs. pre-trained paradigm;(2) new frontiers: some emerging areas in complex SLU as well as the corresponding challenges; (3) abundant open-source resources: to help the community, we have collected, organized the related papers, baseline projects and leaderboard on a public website where SLU researchers could directly access to the recent progress. We hope that this survey can shed a light on future research in SLU field.