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 pre-decision with fixed and flexible policies. We also design a novel computation-aware latency metric, adapted from Average Lagging.
@article{arxiv.2011.02048,
title = {SimulMT to SimulST: Adapting Simultaneous Text Translation to End-to-End Simultaneous Speech Translation},
author = {Xutai Ma and Juan Pino and Philipp Koehn},
journal= {arXiv preprint arXiv:2011.02048},
year = {2020}
}