One challenge in speech translation is that plenty of spoken content is long-form, but short units are necessary for obtaining high-quality translations. To address this mismatch, we adapt large language models (LLMs) to split long ASR transcripts into segments that can be independently translated so as to maximize the overall translation quality. We overcome the tendency of hallucination in LLMs by incorporating finite-state constraints during decoding; these eliminate invalid outputs without requiring additional training. We discover that LLMs are adaptable to transcripts containing ASR errors through prompt-tuning or fine-tuning. Relative to a state-of-the-art automatic punctuation baseline, our best LLM improves the average BLEU by 2.9 points for English-German, English-Spanish, and English-Arabic TED talk translation in 9 test sets, just by improving segmentation.

翻译：语音翻译面临的一个挑战是：大量口语内容为长语音形式，而获得高质量翻译需要以短单元为基础。为解决这一不匹配问题，我们通过调整大语言模型（LLMs）将长ASR转录文本分割为可独立翻译的片段，从而最大化整体翻译质量。通过在解码过程中引入有限状态约束，我们克服了大语言模型的幻觉倾向；这种约束无需额外训练即可消除无效输出。我们发现，通过提示调优或微调，大语言模型能够适应包含ASR错误的转录文本。相较于当前最先进的自动标点基线方法，在英-德、英-西和英-阿TED演讲翻译的9个测试集中，仅通过改进分段策略，我们的最佳大语言模型便将平均BLEU值提升了2.9分。