Towards Efficient Simultaneous Speech Translation: CUNI-KIT System for Simultaneous Track at IWSLT 2023

Abstract

In this paper, we describe our submission to the Simultaneous Track at IWSLT 2023. This year, we continue with the successful setup from the last year, however, we adopt the latest methods that further improve the translation quality.

Additionally, we propose a novel online policy based on CTC. We show that the proposed CTC online policy can be applied to both streaming blockwise models and offline encoder-decoder models.

We observe significant improvements in quality (up to 1.1 BLEU) and the computational footprint (up to 45% relative RTF).

Keywords

• Efficient
• Speech
• Translation