Over-Generation Cannot Be Rewarded: Length-Adaptive Average Lagging for Simultaneous Speech Translation. (arXiv:2206.05807v2 [cs.CL] UPDATED)

Simultaneous speech translation (SimulST) systems aim at generating their
output with the lowest possible latency, which is normally computed in terms of
Average Lagging (AL). In this paper we highlight that, despite its widespread
adoption, AL provides underestimated scores for systems that generate longer
predictions compared to the corresponding references. We also show that this
problem has practical relevance, as recent SimulST systems have indeed a
tendency to over-generate. As a solution, we propose LAAL (Length-Adaptive
Average Lagging), a modified …

arxiv generation speech translation