A popular approach to streaming speech translation is to employ a single offline model with a wait-k policy to support different latency requirements, which is simpler than training multiple online models with different latency constraints. However, there is a mismatch problem in using a model trained with complete utterances for streaming inference with partial input. We demonstrate that speech representations extracted at the end of a streaming input are significantly different from those extracted from a complete utterance. To address this issue, we propose a new approach called Future-Aware Streaming Translation (FAST) that adapts an offline ST model for streaming input. FAST includes a Future-Aware Inference (FAI) strategy that incorporates future context through a trainable masked embedding, and a Future-Aware Distillation (FAD) framework that transfers future context from an approximation of full speech to streaming input. Our experiments on the MuST-C EnDe, EnEs, and EnFr benchmarks show that FAST achieves better trade-offs between translation quality and latency than strong baselines. Extensive analyses suggest that our methods effectively alleviate the aforementioned mismatch problem between offline training and online inference.

翻译：流式语音翻译的一种常见方法是采用单一的离线模型结合wait-k策略以满足不同延迟需求，这比训练多个不同延迟约束的在线模型更为简便。然而，使用完整语句训练的模型进行部分输入的流式推理时存在不匹配问题。我们证明，流式输入结束时提取的语音表示与完整语句提取的表示存在显著差异。为解决这一问题，我们提出了一种名为未来感知流式翻译（FAST）的新方法，该方法使离线语音翻译模型适应流式输入。FAST包含未来感知推理（FAI）策略，通过可训练的掩码嵌入融入未来上下文，以及未来感知蒸馏（FAD）框架，将近似完整语音的未来上下文迁移至流式输入。在MuST-C英德、英西和英法基准上的实验表明，FAST在翻译质量与延迟之间实现了比强基线更优的权衡。大量分析表明，我们的方法有效缓解了离线训练与在线推理之间上述的不匹配问题。