RAG / 检索增强生成

End-to-end Contrastive Language-Speech Pretraining Model For Long-form Spoken Question Answering

端到端对比语言-语音预训练模型用于长形式语音问答

Jiliang Hu, Zuchao Li, Baoyuan Qi, Liu Guoming, Ping Wang

专题命中 知识库问答 ：retrieval augmented generation(abstract)；retriever(abstract)；分类 cs.CL

AI总结 本文提出CLSR模型，通过将音频特征转换为文本表示，提升长音频问答任务的性能，实验表明其优于现有方法。

Comments 12 pages, 7 figures, accepted by AAAI 2026