SimulMT to SimulST: Adapting Simultaneous Text Translation to End-to-End Simultaneous Speech Translation

Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL)


Simultaneous text translation and end-to-end speech translation have recently made great progress but little work has combined these tasks together. We investigate how to adapt simultaneous text translation methods such as wait-k and monotonic multihead attention to end-to-end simultaneous speech translation by introducing a pre-decision module. A detailed analysis is provided on the latency-quality trade-offs of combining fixed and flexible predecision with fixed and flexible policies. We also design a novel computation-aware latency metric, adapted from Average Lagging.

Latest Publications

Boosted Dense Retriever

Patrick Lewis, Barlas Oğuz, Wenhan Xiong, Fabio Petroni, Wen-tau Yih, Sebastian Riedel

NAACL - 2022