MoE-SLU: Towards ASR-Robust Spoken Language Understanding via Mixture-of-Experts

Xuxin Cheng, Zhihong Zhu, Xianwei Zhuang, Zhanpeng Chen, Zhiqi Huang, Yuexian Zou


Abstract
As a crucial task in the task-oriented dialogue systems, spoken language understanding (SLU) has garnered increasing attention. However, errors from automatic speech recognition (ASR) often hinder the performance of understanding. To tackle this problem, we propose MoE-SLU, an ASR-Robust SLU framework based on the mixture-of-experts technique. Specifically, we first introduce three strategies to generate additional transcripts from clean transcripts. Then, we employ the mixture-of-experts technique to weigh the representations of the generated transcripts, ASR transcripts, and the corresponding clean manual transcripts. Additionally, we also regularize the weighted average of predictions and the predictions of ASR transcripts by minimizing the Jensen-Shannon Divergence (JSD) between these two output distributions. Experiment results on three benchmark SLU datasets demonstrate that our MoE-SLU achieves state-of-the-art performance. Further model analysis also verifies the superiority of our method.
Anthology ID:
2024.findings-acl.882
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14868–14879
Language:
URL:
https://aclanthology.org/2024.findings-acl.882
DOI:
10.18653/v1/2024.findings-acl.882
Bibkey:
Cite (ACL):
Xuxin Cheng, Zhihong Zhu, Xianwei Zhuang, Zhanpeng Chen, Zhiqi Huang, and Yuexian Zou. 2024. MoE-SLU: Towards ASR-Robust Spoken Language Understanding via Mixture-of-Experts. In Findings of the Association for Computational Linguistics: ACL 2024, pages 14868–14879, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
MoE-SLU: Towards ASR-Robust Spoken Language Understanding via Mixture-of-Experts (Cheng et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.882.pdf