直接语音到文本翻译的最新进展
Recent Advances in Direct Speech-to-text Translation
AI总结：
本文综述直接语音翻译的最新进展，按建模负担、数据稀缺和应用问题三大挑战分类，总结编码器-解码器与多任务框架、数据增强等技术，并展望未来方向。
摘要：
近年来，语音到文本翻译吸引了越来越多的关注，许多研究迅速涌现。本文对直接语音翻译进行了全面综述，旨在总结当前最先进的技术。首先，我们根据主要挑战——建模负担、数据稀缺和应用问题——将现有研究工作分为三个方向。为解决建模负担问题，提出了两种主要结构：编码器-解码器框架（Transformer及其变体）和多任务框架。针对数据稀缺的挑战，近期工作借助了许多复杂技术，如数据增强、预训练、知识蒸馏和多语言建模。我们分析并总结了应用问题，包括实时性、分段、命名实体、性别偏见和语码转换。最后，我们讨论了未来工作的一些有前景的方向。
英文摘要：
Recently, speech-to-text translation has attracted more and more attention and many studies have emerged rapidly. In this paper, we present a comprehensive survey on direct speech translation aiming to summarize the current state-of-the-art techniques. First, we categorize the existing research work into three directions based on the main challenges -- modeling burden, data scarcity, and application issues. To tackle the problem of modeling burden, two main structures have been proposed, encoder-decoder framework (Transformer and the variants) and multitask frameworks. For the challenge of data scarcity, recent work resorts to many sophisticated techniques, such as data augmentation, pre-training, knowledge distillation, and multilingual modeling. We analyze and summarize the application issues, which include real-time, segmentation, named entity, gender bias, and code-switching. Finally, we discuss some promising directions for future work.
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。
