End-to-end speech-to-text translation models are often initialized with
pre-trained speech encoder and pre-trained text decoder. This leads to a
significant training gap between pre-training and fine-tuning, largely due to
the modality differences between speech outputs from the encoder and text
inputs to the decoder. In this work, we aim to bridge the modality gap between
speech and text to improve translation quality. We propose M-Adapter, a novel
Transformer-based module, to adapt speech representations to text. While
shrinking the speech sequence, M-Adapter produces features desired for
speech-to-text translation via modelling global and local dependencies of a
speech sequence. Our experimental results show that our model outperforms a
strong baseline by up to 1 BLEU score on the Must-C En$\rightarrow$DE
dataset.\footnote{Our code is available at
this https URL.}

本研究提出一种新型基于 Transformer 的 M-Adapter 方法，通过建模语音序列的全局和局部依赖关系，将语音表示特征适应到文字输入上，以缩小语音输出和文字输入之间的模态差距，从而提高端到端语音到文本翻译的质量，并在 Must-C En→DE 数据集上获得比强基准模型高达 1 BLEU 得分的表现。