SimulMT to SimulST: Adapting Simultaneous Text Translation to End-to-End Simultaneous Speech Translation
arXiv:2011.02048
Abstract
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.
Cited by in corpus (6)
- Over-Generation Cannot Be Rewarded: Length-Adaptive Average Lagging for Simultaneous Speech Translation
- End-to-End Simultaneous Speech Translation with Differentiable Segmentation
- Does Simultaneous Speech Translation need Simultaneous Models?
- Attention as a Guide for Simultaneous Speech Translation
- SimulLR: Simultaneous Lip Reading Transducer with Attention-Guided Adaptive Memory
- Direct Models for Simultaneous Translation and Automatic Subtitling: FBK@IWSLT2023