论文标题
同时语音翻译需要同时模型吗？
Does Simultaneous Speech Translation need Simultaneous Models?
论文作者
论文摘要
在同时的语音翻译（Simulst）中，找到高译出质量和低潜伏期之间的最佳权衡是一项艰巨的任务。为了满足不同应用程序方案所带来的延迟约束，通常对多个专用的Simulst模型进行培训和维护，从而产生高计算成本。在本文中，受这些成本造成的社会和环境影响增加的动机，我们研究了一个经过培训的单个模型不仅可以服务于离线，而且还可以同时服务，而无需进行任何其他培训或适应。关于EN-> {DE，ES}的实验表明，除了促进良好的离线技术和体系结构的采用而不会影响潜伏期外，离线解决方案还具有与同时培训的相同模型相比，具有相似或更好的翻译质量，以及与Art的Simulst of Art的模拟状态相比。
In simultaneous speech translation (SimulST), finding the best trade-off between high translation quality and low latency is a challenging task. To meet the latency constraints posed by the different application scenarios, multiple dedicated SimulST models are usually trained and maintained, generating high computational costs. In this paper, motivated by the increased social and environmental impact caused by these costs, we investigate whether a single model trained offline can serve not only the offline but also the simultaneous task without the need for any additional training or adaptation. Experiments on en->{de, es} indicate that, aside from facilitating the adoption of well-established offline techniques and architectures without affecting latency, the offline solution achieves similar or better translation quality compared to the same model trained in simultaneous settings, as well as being competitive with the SimulST state of the art.
