AdaTranS: Adapting with Boundary-based Shrinking for End-to-End Speech Translation

Zeng, Xingshan, Li, Liangyou, Liu, Qun

arXiv.org Artificial Intelligence 

To alleviate the data scarcity problem in End-to-end speech translation (ST), pre-training on data for speech recognition and machine translation is considered as an important technique. However, the modality gap between speech and text prevents the ST model from efficiently inheriting knowledge from the pre-trained models. In this work, we propose AdaTranS for end-to-end ST. It adapts the speech features with a new shrinking mechanism to mitigate the length mismatch between speech and text features by predicting word boundaries. Experiments on the MUST-C dataset demonstrate that AdaTranS achieves better performance than the other shrinking-based methods, with higher inference speed and lower memory usage. Further experiments also show that AdaTranS can be equipped with additional alignment losses to further improve performance.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found