Joint Training And Decoding for Multilingual End-to-End Simultaneous Speech Translation
This work addresses real-world applications of multilingual speech translation, but it is incremental as it builds on existing end-to-end approaches.
The paper tackles multilingual simultaneous speech translation by proposing joint training and decoding methods, achieving effective results on a curated dataset.
Recent studies on end-to-end speech translation(ST) have facilitated the exploration of multilingual end-to-end ST and end-to-end simultaneous ST. In this paper, we investigate end-to-end simultaneous speech translation in a one-to-many multilingual setting which is closer to applications in real scenarios. We explore a separate decoder architecture and a unified architecture for joint synchronous training in this scenario. To further explore knowledge transfer across languages, we propose an asynchronous training strategy on the proposed unified decoder architecture. A multi-way aligned multilingual end-to-end ST dataset was curated as a benchmark testbed to evaluate our methods. Experimental results demonstrate the effectiveness of our models on the collected dataset. Our codes and data are available at: https://github.com/XiaoMi/TED-MMST.