首个语音翻译导师制实践，探索多语言系统与数据增强方法。
SpeechT: Findings of the First Mentorship in Speech Translation
- 组织首次语音翻译导师制，聚焦数据准备与建模
- 对比端到端与级联式系统，验证多语言适配性
- 覆盖阿拉伯语等6种非英语语言，推动跨语言研究
本文详述了2024年12月与2025年1月举行的首届语音翻译（SpeechT）导师制活动。参与者围绕数据准备、建模及前沿研究展开工作，探索数据增强技术，并对比端到端与级联式语音翻译系统。项目涵盖阿拉伯语、孟加拉语、加利西亚语、印度尼西亚语、日语和西班牙语等多种非英语语言，为多语言语音翻译提供实践参考。
原文摘要 · Abstract (English)
This work presents the details and findings of the first mentorship in speech translation (SpeechT), which took place in December 2024 and January 2025. To fulfil the mentorship requirements, the participants engaged in key activities, including data preparation, modelling, and advanced research. The participants explored data augmentation techniques and compared end-to-end and cascaded speech translation systems. The projects covered various languages other than English, including Arabic, Bengali, Galician, Indonesian, Japanese, and Spanish.
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。