End-to-end Speech Translation (E2E ST) aims to directly translate source speech into target text. Existing ST methods perform poorly when only extremely small speech-text data are available for training. We observe that an ST model's performance closely correlates with its embedding similarity between speech and source transcript. In this paper, we propose Word-Aligned COntrastive learning (WACO), a simple and effective method for extremely low-resource speech-to-text translation. Our key idea is bridging word-level representations for both speech and text modalities via contrastive learning. We evaluate WACO and other methods on the MuST-C dataset, a widely used ST benchmark, and on a low-resource direction Maltese-English from IWSLT 2023. Our experiments demonstrate that WACO outperforms the best baseline by 9+ BLEU points with only 1-hour parallel ST data. Code is available at https://github.com/owaski/WACO.

翻译：端到端语音翻译（E2E ST）旨在直接将源语言语音翻译为目标文本。现有的语音翻译方法在仅有极少量语音-文本数据可用于训练时表现不佳。我们观察到，语音翻译模型的性能与其语音和源语言转录之间的嵌入相似度密切相关。本文提出词对齐对比学习（WACO），一种针对极低资源语音到文本翻译的简单而有效的方法。我们的核心思想是通过对比学习桥接语音和文本模态的词级表示。我们在广泛使用的语音翻译基准数据集MuST-C以及IWSLT 2023的低资源方向马耳他语-英语上评估了WACO及其他方法。实验表明，在仅有1小时并行语音翻译数据的情况下，WACO相比最优基线模型提升了9个以上的BLEU分数。代码已在https://github.com/owaski/WACO开源。