LongAudio-RAG: Event-Grounded Question Answering over Multi-Hour Long Audio
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917324059049984 |
|---|---|
| author | Vakada, Naveen Hegde, Kartik Sridhar, Arvind Krishna Guo, Yinyi Visser, Erik |
| author_facet | Vakada, Naveen Hegde, Kartik Sridhar, Arvind Krishna Guo, Yinyi Visser, Erik |
| contents | Long-duration audio is increasingly common in industrial and consumer settings, yet reviewing multi-hour recordings is impractical, motivating systems that answer natural-language queries with precise temporal grounding and minimal hallucination. Existing audio-language models show promise, but long-audio question answering remains difficult due to context-length limits. We introduce LongAudio-RAG (LA-RAG), a hybrid framework that grounds Large Language Model outputs in retrieved, timestamped acoustic event detections rather than raw audio. Multi-hour streams are converted into structured event records stored in an SQL database, and at inference time the system resolves natural-language time references, classifies intent, retrieves only the relevant events, and generates answers using this constrained evidence. To evaluate performance, we construct a synthetic long-audio benchmark by concatenating recordings with preserved timestamps and generating template-based question-answer pairs for detection, counting, and summarization tasks. Finally, we demonstrate the practicality of our approach by deploying it in a hybrid edge-cloud environment, where the audio grounding model runs on-device on IoT-class hardware while the LLM is hosted on a GPU-backed server. This architecture enables low-latency event extraction at the edge and high-quality language reasoning in the cloud. Experiments show that structured, event-level retrieval significantly improves accuracy compared to vanilla Retrieval-Augmented Generation (RAG) or text-to-SQL approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_14612 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LongAudio-RAG: Event-Grounded Question Answering over Multi-Hour Long Audio Vakada, Naveen Hegde, Kartik Sridhar, Arvind Krishna Guo, Yinyi Visser, Erik Audio and Speech Processing Artificial Intelligence Machine Learning Long-duration audio is increasingly common in industrial and consumer settings, yet reviewing multi-hour recordings is impractical, motivating systems that answer natural-language queries with precise temporal grounding and minimal hallucination. Existing audio-language models show promise, but long-audio question answering remains difficult due to context-length limits. We introduce LongAudio-RAG (LA-RAG), a hybrid framework that grounds Large Language Model outputs in retrieved, timestamped acoustic event detections rather than raw audio. Multi-hour streams are converted into structured event records stored in an SQL database, and at inference time the system resolves natural-language time references, classifies intent, retrieves only the relevant events, and generates answers using this constrained evidence. To evaluate performance, we construct a synthetic long-audio benchmark by concatenating recordings with preserved timestamps and generating template-based question-answer pairs for detection, counting, and summarization tasks. Finally, we demonstrate the practicality of our approach by deploying it in a hybrid edge-cloud environment, where the audio grounding model runs on-device on IoT-class hardware while the LLM is hosted on a GPU-backed server. This architecture enables low-latency event extraction at the edge and high-quality language reasoning in the cloud. Experiments show that structured, event-level retrieval significantly improves accuracy compared to vanilla Retrieval-Augmented Generation (RAG) or text-to-SQL approaches. |
| title | LongAudio-RAG: Event-Grounded Question Answering over Multi-Hour Long Audio |
| topic | Audio and Speech Processing Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2602.14612 |