CMOT: Cross-modal Mixup via Optimal Transport for Speech Translation
This work addresses the data scarcity and modality gap in speech translation, offering a novel method that improves performance for cross-modal translation tasks.
The paper tackles the modality gap between speech and text in end-to-end speech translation by proposing Cross-modal Mixup via Optimal Transport (CMOT), which aligns and mixes sequences from different modalities, achieving an average BLEU score of 30.0 on the MuST-C benchmark across 8 translation directions.
End-to-end speech translation (ST) is the task of translating speech signals in the source language into text in the target language. As a cross-modal task, end-to-end ST is difficult to train with limited data. Existing methods often try to transfer knowledge from machine translation (MT), but their performances are restricted by the modality gap between speech and text. In this paper, we propose Cross-modal Mixup via Optimal Transport CMOT to overcome the modality gap. We find the alignment between speech and text sequences via optimal transport and then mix up the sequences from different modalities at a token level using the alignment. Experiments on the MuST-C ST benchmark demonstrate that CMOT achieves an average BLEU of 30.0 in 8 translation directions, outperforming previous methods. Further analysis shows CMOT can adaptively find the alignment between modalities, which helps alleviate the modality gap between speech and text. Code is publicly available at https://github.com/ictnlp/CMOT.