新型Omni-Embed-Audio模型利用LLM增强音频-文本检索

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-02 04:00

研究人员开发了Omni-Embed-Audio (OEA)，一种新的面向检索的编码器，它利用多模态大型语言模型来改进音频-文本检索。与依赖字幕式查询的先前系统不同，OEA旨在处理更自然的搜索行为，包括问题、命令和否定查询。实验表明，OEA在文本到音频检索方面的性能与现有的最先进模型相当，而在文本到文本检索和区分听起来相似的音频片段的能力方面，其性能显著优于它们。 AI

影响引入了一种更强大的音频-文本检索方法，有可能改进多模态AI应用中的搜索功能。

排序理由这是一篇描述新模型和评估方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇描述新模型和评估方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 119 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · HaeJun Yoo, Yongseop Shin, Insung Lee, Myoung-Wan Koo, Du-Seong Chang · 2026-06-02 04:00

Omni-Embed-Audio：利用多模态大语言模型实现鲁棒的音频-文本检索

arXiv:2604.18360v2 Announce Type: replace-cross Abstract: Audio-text retrieval systems based on Contrastive Language-Audio Pretraining (CLAP) achieve strong performance on traditional benchmarks; however, these benchmarks rely on caption-style queries that differ substantially fr…

本文如何被排名

报道来源 [1]

Omni-Embed-Audio：利用多模态大语言模型实现鲁棒的音频-文本检索

相关实体

相关话题