This paper describes the FBK's participation in the Simultaneous Translation
and Automatic Subtitling tracks of the IWSLT 2023 Evaluation Campaign. Our
submission focused on the use of direct architectures to perform both tasks:
for the simultaneous one, we leveraged the knowledge already acquired by
offline-trained models and directly applied a policy to obtain the real-time
inference; for the subtitling one, we adapted the direct ST model to produce
well-formed subtitles and exploited the same architecture to produce timestamps
needed for the subtitle synchronization with audiovisual content. Our
English-German SimulST system shows a reduced computational-aware latency
compared to the one achieved by the top-ranked systems in the 2021 and 2022
rounds of the task, with gains of up to 3.5 BLEU. Our automatic subtitling
system outperforms the only existing solution based on a direct system by 3.7
and 1.7 SubER in English-German and English-Spanish respectively.

该论文描述了 FBK 参与 IWSLT 2023 评估活动中的同时翻译和自动字幕轨道。我们的提交重点是使用直接架构来执行这两项任务：对于同时翻译，我们利用了离线训练模型已经获得的知识，并直接应用策略获得实时推理结果；对于字幕，我们对直接 ST 模型进行了调整，生成了符合规范的字幕，并利用相同的架构生成了与视听内容同步的时间戳。与 2021 年和 2022 年任务的排名前几位系统相比，我们的英德 SimulST 系统显示出更低的计算感知延迟，BLEU 提高了最多 3.5 分。我们的自动字幕系统在英德和英西文中分别比基于直接系统的唯一现有解决方案优于 3.7 和 1.7 SubER。