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型语言模型（LLMs）连接起来，以进行高级语音处理任务。该系统通过支持28种欧洲语言的端到端自动语音识别（ASR）来扩展现有的单语投影仪，并且可以进一步适配其他语言。MEUSLI还展示了超越ASR的能力，能够以最小的任务特定监督来促进多语言语音翻译和主题识别。 AI
影响 推动了多语言语音理解和翻译能力的发展，有可能拓宽基于LLM的语音技术的应用范围。
排序理由 该集群描述了关于使用LLMs进行多语言语音处理的新方法和系统的研究论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2607.25716v1 Announce Type: new Abstract: Federated learning (FL) enables privacy-preserving training of automatic speech recognition (ASR) systems across distributed data sources, yet its application to large-scale speech language models (SpeechLLMs) remains unexplored. Th…
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…