An Empirical Study of Consistency Regularization for End-to-End Speech-to-Text Translation
Pengzhi Gao, Ruiqing Zhang, Zhongjun He, Hua Wu, Haifeng Wang
Abstract
Consistency regularization methods, such as R-Drop (Liang et al., 2021) and CrossConST (Gao et al., 2023), have achieved impressive supervised and zero-shot performance in the neural machine translation (NMT) field. Can we also boost end-to-end (E2E) speech-to-text translation (ST) by leveraging consistency regularization? In this paper, we conduct empirical studies on intra-modal and cross-modal consistency and propose two training strategies, SimRegCR and SimZeroCR, for E2E ST in regular and zero-shot scenarios. Experiments on the MuST-C benchmark show that our approaches achieve state-of-the-art (SOTA) performance in most translation directions. The analyses prove that regularization brought by the intra-modal consistency, instead of the modality gap, is crucial for the regular E2E ST, and the cross-modal consistency could close the modality gap and boost the zero-shot E2E ST performance.
BibTeX
@inproceedings{gao-etal-2024-empirical,
title = "An Empirical Study of Consistency Regularization for End-to-End Speech-to-Text Translation",
author = "Gao, Pengzhi and
Zhang, Ruiqing and
He, Zhongjun and
Wu, Hua and
Wang, Haifeng",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.14/",
doi = "10.18653/v1/2024.naacl-long.14",
pages = "242--256"
}