AudioRAG+: Feedback-driven Retrieval-augmented Audio Generation with Large Audio Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910024878522368 |
|---|---|
| author | Zhao, Junqi Li, Chenxing Zhao, Jinzheng Chen, Rilin Yu, Dong Plumbley, Mark D. Wang, Wenwu |
| author_facet | Zhao, Junqi Li, Chenxing Zhao, Jinzheng Chen, Rilin Yu, Dong Plumbley, Mark D. Wang, Wenwu |
| contents | We propose a general feedback-driven retrieval-augmented generation (RAG) approach that leverages Large Audio Language Models (LALMs) to address the missing or imperfect synthesis of specific sound events in text-to-audio (TTA) generation. Unlike previous RAG-based TTA methods that typically train specialized models from scratch, we utilize LALMs to analyze audio generation outputs, retrieve concepts that pre-trained models struggle to generate from an external database, and incorporate the retrieved information into the generation process. Experimental results show that our method not only enhances the ability of LALMs to identify missing sound events but also delivers improvements across different models, outperforming existing RAG-specialized approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_01091 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AudioRAG+: Feedback-driven Retrieval-augmented Audio Generation with Large Audio Language Models Zhao, Junqi Li, Chenxing Zhao, Jinzheng Chen, Rilin Yu, Dong Plumbley, Mark D. Wang, Wenwu Sound We propose a general feedback-driven retrieval-augmented generation (RAG) approach that leverages Large Audio Language Models (LALMs) to address the missing or imperfect synthesis of specific sound events in text-to-audio (TTA) generation. Unlike previous RAG-based TTA methods that typically train specialized models from scratch, we utilize LALMs to analyze audio generation outputs, retrieve concepts that pre-trained models struggle to generate from an external database, and incorporate the retrieved information into the generation process. Experimental results show that our method not only enhances the ability of LALMs to identify missing sound events but also delivers improvements across different models, outperforming existing RAG-specialized approaches. |
| title | AudioRAG+: Feedback-driven Retrieval-augmented Audio Generation with Large Audio Language Models |
| topic | Sound |
| url | https://arxiv.org/abs/2511.01091 |