Abstract
Recent work on Speech-to-Text Translation (S2TT) has focused on LLM-based models, introducing the increasingly adopted Chain-of-Thought (CoT) prompting, where the model is guided to first transcribe the speech and then translate it. CoT typically outperforms direct prompting primarily because it can exploit abundant Automatic Speech Recognition (ASR) and Text-to-Text Translation (T2TT) datasets to explicitly model its steps. In this paper, we systematically compare CoT and Direct prompting under increasing amounts of S2TT data. To this end, we pseudo-label an ASR corpus by translating its transcriptions into six European languages, and train LLM-based S2TT systems with both prompting strategies at different data scales. Our results show that Direct improves more consistently as the amount of data increases, suggesting that it may become a more effective approach as larger S2TT resources are created.
Abstract (translated)
最近关于语音到文本翻译（S2TT）的工作主要集中在基于大型语言模型（LLM）的模型上，引入了日益流行的链式思维（CoT）提示机制，在这种机制下，模型被引导首先转录语音然后进行翻译。CoT通常比直接提示表现更好，主要是因为它可以利用大量的自动语音识别（ASR）和文本到文本翻译（T2TT）数据集来显式地建模其步骤。在本文中，我们系统性地比较了在不断增加的S2TT数据量下CoT和直接提示的表现。为此，我们将一个ASR语料库伪标签化为六种欧洲语言，并使用这两种提示策略以不同的数据规模训练基于LLM的S2TT系统。我们的结果显示，随着数据量的增加，直接提示的一致性表现更好，这表明在更大规模的S2TT资源被创建时，它可能会成为一个更有效的策略。
URL
https://arxiv.org/abs/2510.03093
