activity
20222024
most citedA Dynamic Graph Interactive Framework with Label-Semantic Injection for Spoken Language Understanding

6 citations · 14 across the 10 of their papers we have counts for

collaborators

10 papers

cs.SD2024

DiffATR: Diffusion-based Generative Modeling for Audio-Text Retrieval

Yifei Xin, Xuxin Cheng, Zhihong Zhu +2

Existing audio-text retrieval (ATR) methods are essentially discriminative models that aim to maximize the conditional likelihood, represented as p(candidates|query). Nevertheless,…

cs.SD2024★ 1 cited

Audio-text Retrieval with Transformer-based Hierarchical Alignment and Disentangled Cross-modal Representation

Yifei Xin, Zhihong Zhu, Xuxin Cheng +2

Most existing audio-text retrieval (ATR) approaches typically rely on a single-level interaction to associate audio and text, limiting their ability to align different modalities a…

cs.CL2024

Towards Spoken Language Understanding via Multi-level Multi-grained Contrastive Learning

Xuxin Cheng, Wanshi Xu, Zhihong Zhu +2

Spoken language understanding (SLU) is a core task in task-oriented dialogue systems, which aims at understanding the user's current goal through constructing semantic frames. SLU…

cs.CL2023

ML-LMCL: Mutual Learning and Large-Margin Contrastive Learning for Improving ASR Robustness in Spoken Language Understanding

Xuxin Cheng, Bowen Cao, Qichen Ye +3

Spoken language understanding (SLU) is a fundamental task in the task-oriented dialogue systems. However, the inevitable errors from automatic speech recognition (ASR) usually impa…

cs.CV2023★ 3 cited

G2L: Semantically Aligned and Uniform Video Grounding via Geodesic and Game Theory

Hongxiang Li, Meng Cao, Xuxin Cheng +3

The recent video grounding works attempt to introduce vanilla contrastive learning into video grounding. However, we claim that this naive solution is suboptimal. Contrastive learn…

cs.CL2023

TLAG: An Informative Trigger and Label-Aware Knowledge Guided Model for Dialogue-based Relation Extraction

Hao An, Dongsheng Chen, Weiyuan Xu +2

Dialogue-based Relation Extraction (DRE) aims to predict the relation type of argument pairs that are mentioned in dialogue. The latest trigger-enhanced methods propose trigger pre…