多语言长篇语音指令跟随：KIT 在 IWSLT 2026 的提交
Multilingual Long-Form Speech Instruction Following: KIT's Submission to IWSLT 2026
AI总结：
提出一种通用数据增强流水线，通过片段拼接、LLM标签生成和跨语言翻译将短语音语料转换为长语音训练数据，结合似然与最小贝叶斯风险解码解决长语音语义任务退化问题。
摘要：
随着大语言模型的出现，单任务和基于标记的多任务模型已演变为基于指令的系统，该系统从自然语言提示中隐式推断任务和目标语言。这一趋势反映在IWSLT的指令跟随赛道中，该赛道今年引入了包括未知惊喜任务在内的新任务，对已知任务的过拟合构成了真正的挑战。我们展示了KIT在无约束设置下对长指令和短指令跟随赛道的提交。我们的方法结合了一个通用数据增强流水线，通过片段拼接、基于LLM的标签生成和跨语言翻译将短语音语料转换为长语音训练数据，在六个任务和四种语言上产生了超过100万个实例。我们进一步表明，基于似然的重新排序虽然对ASR非常有效，但会系统地降低语义任务，通过选择从分段音频处理而非整体长语音推理中生成的候选者，这一失败模式通过将似然与最小贝叶斯风险解码相结合得以解决。
英文摘要：
With the advent of Large Language Models, single-task and token-based multi-task models have evolved into instruction-based systems that infer task and target language implicitly from natural language prompts. This trend is reflected in IWSLT's Instruction Following Track, which this year introduced new tasks including an unknown surprise task, posing a genuine challenge against overfitting to known tasks. We present KIT's submission to the Long and Short Instruction Following tracks in the unconstrained setting. Our approach combines a general data augmentation pipeline that converts short-form corpora into long-form training data through segment concatenation, LLM-based label generation, and cross-lingual translation, yielding over 1M instances across six tasks and four languages. We further show that likelihood-based re-ranking, while highly effective for ASR, systematically degrades semantic tasks by spuriously selecting candidates generated from segmented audio processing rather than holistic long-form inference, a failure mode resolved by combining likelihood with Minimum Bayes Risk decoding.
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。
