研究人员开发了MEUSLI，这是一种新颖的多语言投影仪，旨在将语音编码器与大语言模型（LLM）连接起来，以完成高级语音处理任务。该系统扩展了现有的单语投影仪，支持28种欧洲语言的端到端自动语音识别（ASR），并且可以进一步适应其他语言。MEUSLI还展示了超越ASR的能力，只需极少的特定任务监督即可实现多语言语音翻译和主题识别。 AI
影响 推进了多语言语音理解和翻译能力，有可能拓宽基于LLM的语音技术的获取途径。
排序理由 该集群描述了详细介绍使用LLM进行多语言语音处理的新方法和系统的新研究论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2607.22100v1 Announce Type: new Abstract: Lightweight projectors are an established way to connect pre-trained speech encoders with large language models (LLMs), mapping acoustic features into token-level embeddings for tasks like ASR and spoken question answering. Existing…
arXiv:2603.07025v2 Announce Type: replace Abstract: Speech Large Language Models (LLMs) that understand and follow instructions in many languages are useful for real-world interaction, but are difficult to train with supervised fine-tuning, requiring large, task-specific speech c…