通过分析梯度自动优化多语言语音翻译的共享结构，提升低资源场景表现。
Gradient-Informed Training for Low-Resource Multilingual Speech Translation
- 根据梯度信息动态确定每层的语言共享模式
- 在四种语言对上显著提升翻译质量
- 适合低资源多语言语音翻译研究者参考
在低资源多语言语音到文本翻译中，跨语言统一架构常引发表示冲突，阻碍模型收敛。本文提出一种基于梯度信息的系统性方法，自动识别层级共享模式。通过三种分析策略：基于距离的语言聚类、自任务/跨任务发散度度量以分配容量，以及联合分解结合典型相关分析实现子空间对齐。在四个语言对（采用SeamlessM4T-Medium架构）上进行充分评估，持续提升翻译质量指标。
原文摘要 · Abstract (English)
In low-resource multilingual speech-to-text translation, uniform architectural sharing across languages frequently introduces representation conflicts that impede convergence. This work proposes a principled methodology to automatically determine layer-specific sharing patterns by mining training gradient information. Our approach employs three distinct analysis strategies: distance-based language clustering, self/cross-task divergence metrics for capacity allocation, and joint factorization coupled with canonical correlation analysis for subspace alignment. Extensive evaluation across four language pairs (using the SeamlessM4T-Medium architecture) demonstrates persistent improvements in translation quality metrics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。