Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?
This resolves a long-standing debate in speech translation by showing that direct methods have caught up to traditional cascade approaches, though it is incremental as it confirms existing trends.
The study systematically compared cascade and direct speech translation systems on three language directions, finding that the performance gap between the two paradigms is now closed, with no significant human preference or ability to distinguish them.
Five years after the first published proofs of concept, direct approaches to speech translation (ST) are now competing with traditional cascade solutions. In light of this steady progress, can we claim that the performance gap between the two is closed? Starting from this question, we present a systematic comparison between state-of-the-art systems representative of the two paradigms. Focusing on three language directions (English-German/Italian/Spanish), we conduct automatic and manual evaluations, exploiting high-quality professional post-edits and annotations. Our multi-faceted analysis on one of the few publicly available ST benchmarks attests for the first time that: i) the gap between the two paradigms is now closed, and ii) the subtle differences observed in their behavior are not sufficient for humans neither to distinguish them nor to prefer one over the other.