提升同声语音翻译的稳定性：一种修订可控的解码方法
Improving Stability in Simultaneous Speech Translation: A Revision-Controllable Decoding Approach
AI总结：
针对同声语音翻译中部分结果闪烁的稳定性问题，提出一种在束搜索剪枝中引入允许修订窗口的修订可控解码方法，可大幅减少甚至消除闪烁，在保障翻译质量的同时显著提升解码稳定性。
摘要：
同声语音到文本翻译在实时跨语言交流中发挥着关键作用。尽管近年来取得了诸多进展，翻译过程的稳定性仍面临挑战，这一问题主要体现为部分翻译结果的闪烁现象。本文提出了一种新颖的修订可控方法以解决该问题。该方法在束搜索剪枝过程中引入一个允许修订窗口，筛除可能引发大量修订的候选译文，从而大幅减少闪烁现象，更关键的是具备完全消除闪烁的能力。实验表明，所提方法能显著提升解码稳定性，且不会大幅损害翻译质量。
英文摘要：
Simultaneous Speech-to-Text translation serves a critical role in real-time crosslingual communication. Despite the advancements in recent years, challenges remain in achieving stability in the translation process, a concern primarily manifested in the flickering of partial results. In this paper, we propose a novel revision-controllable method designed to address this issue. Our method introduces an allowed revision window within the beam search pruning process to screen out candidate translations likely to cause extensive revisions, leading to a substantial reduction in flickering and, crucially, providing the capability to completely eliminate flickering. The experiments demonstrate the proposed method can significantly improve the decoding stability without compromising substantially on the translation quality.
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。
