HARP: Agentic Hybrid Retrieval and Analysis for Long-Form Audio

2026-09-12

AI Summary

研究通过结合关键词和向量搜索的混合检索方法，提高长音频分析中证据定位与整合的准确性，引入HARP框架以优化性能评估。

Abstract

Long-form audio analysis requires systems to localize and integrate evidence distributed across extended recordings. While existing work primarily retrieves semantic content through structured textual representations, many real-world queries depend on acoustic evidence that is better preserved in continuous representations or raw audio. We introduce HARP (Hybrid Audio Retrieval Pipeline), an agentic framework and benchmark for systematically studying retrieval and evidence representations in long-audio analysis. Hybrid retrieval combining keyword and vector search shows the most robust performance. When paired with both metadata and retrieved audio as evidence, average answer accuracy improves by around 10% and rationale accuracy by around 6% over single-modality retrieval and evidence. Fine-grained evaluation shows that answer accuracy alone overestimates system capability and that HARP mostly follows human performance trends across query types. These results highlight the importance of combining structured retrieval with flexible access to audio evidence and evaluating long-audio systems beyond answer accuracy.

Problem

• long-form audio analysis
• acoustic evidence
• structured textual representations

Innovation

• Hybrid Retrieval
• Audio Evidence
• Long-Form Audio Analysis
• HARP