PCAD: Towards ASR-Robust Spoken Language Understanding via Prototype Calibration and Asymmetric Decoupling

Xianwei Zhuang, Xuxin Cheng, Liming Liang, Yuxin Xie, Zhichang Wang, Zhiqi Huang, Yuexian Zou


Abstract
Spoken language understanding (SLU) inevitably suffers from error propagation from automatic speech recognition (ASR) in actual scenarios. Some recent works attempt to alleviate this issue through contrastive learning. However, they (1) sample negative pairs incorrectly in pre-training; (2) only focus on implicit metric learning while neglecting explicit erroneous predictions; (3) treat manual and ASR transcripts indiscriminately. In this paper, we propose a novel framework termed PCAD, which can calibrate bias and errors and achieve adaptive-balanced decoupling training. Specifically, PCAD utilizes a prototype-based loss to aggregate label and prediction priors and calibrate bias and error-prone semantics for better inter-class discrimination and intra-class consistency. We theoretically analyze the effect of this loss on robustness enhancement. Further, we leverage a teacher-student model for asymmetric decoupling training between different transcripts and formulate a novel gradient-sensitive exponential moving averaging (GS-EMA) algorithm for adaptive balance of accuracy and robustness. Experiments on three datasets show that PCAD significantly outperforms existing approaches and achieves new state-of-the-art performance.
Anthology ID:
2024.acl-long.286
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5235–5246
Language:
URL:
https://aclanthology.org/2024.acl-long.286
DOI:
10.18653/v1/2024.acl-long.286
Bibkey:
Cite (ACL):
Xianwei Zhuang, Xuxin Cheng, Liming Liang, Yuxin Xie, Zhichang Wang, Zhiqi Huang, and Yuexian Zou. 2024. PCAD: Towards ASR-Robust Spoken Language Understanding via Prototype Calibration and Asymmetric Decoupling. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5235–5246, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
PCAD: Towards ASR-Robust Spoken Language Understanding via Prototype Calibration and Asymmetric Decoupling (Zhuang et al., ACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2024.acl-long.286.pdf