R-BI：正则化批量输入增强增量解码框架以实现低延迟同声传译
R-BI: Regularized Batched Inputs enhance Incremental Decoding Framework for Low-Latency Simultaneous Speech Translation
AI总结：
本文提出正则化批量输入（R-BI）策略，通过增强输入多样性减少增量解码中的输出错误，在IWSLT同声传译任务上实现低延迟且BLEU损失不超过2点，并在多个语言方向取得新最优结果。
摘要：
增量解码是一种有效的框架，它允许在不修改原始模型的情况下在同步场景中使用离线模型，使其适用于低延迟同声传译。然而，当系统从不完整输入中输出时，该框架可能会引入错误。为了减少这些输出错误，可以采用 Hold-$n$、LA-$n$ 和 SP-$n$ 等几种策略，但超参数 $n$ 需要仔细选择以获得最佳性能。此外，这些策略更适合端到端系统而非级联系统。在本文中，我们提出了一种新的自适应且高效的策略，名为“正则化批量输入”（Regularized Batched Inputs）。我们的方法通过增强输入多样性来减少输出错误，从而脱颖而出。我们为端到端系统和级联系统分别提出了特定的正则化技术。我们在 IWSLT 同声传译（SimulST）任务上进行了实验，结果表明我们的方法在保持与离线系统相比不超过 2 个 BLEU 点损失的同时实现了低延迟。此外，我们的 SimulST 系统在多个语言方向上取得了若干新的最先进结果。
英文摘要：
Incremental Decoding is an effective framework that enables the use of an offline model in a simultaneous setting without modifying the original model, making it suitable for Low-Latency Simultaneous Speech Translation. However, this framework may introduce errors when the system outputs from incomplete input. To reduce these output errors, several strategies such as Hold-$n$, LA-$n$, and SP-$n$ can be employed, but the hyper-parameter $n$ needs to be carefully selected for optimal performance. Moreover, these strategies are more suitable for end-to-end systems than cascade systems. In our paper, we propose a new adaptable and efficient policy named "Regularized Batched Inputs". Our method stands out by enhancing input diversity to mitigate output errors. We suggest particular regularization techniques for both end-to-end and cascade systems. We conducted experiments on IWSLT Simultaneous Speech Translation (SimulST) tasks, which demonstrate that our approach achieves low latency while maintaining no more than 2 BLEU points loss compared to offline systems. Furthermore, our SimulST systems attained several new state-of-the-art results in various language directions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
