ResearchTrend.AI
  • Communities
  • Connect sessions
  • AI calendar
  • Organizations
  • Join Slack
  • Contact Sales
Papers
Communities
Social Events
Terms and Conditions
Pricing
Contact Sales
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2511.01091
82
0

Feedback-driven Retrieval-augmented Audio Generation with Large Audio Language Models

2 November 2025
Junqi Zhao
Chenxing Li
Jinzheng Zhao
Rilin Chen
Dong Yu
Mark D. Plumbley
Wenwu Wang
ArXiv (abs)PDFHTML
Main:4 Pages
1 Figures
Bibliography:1 Pages
4 Tables
Abstract

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.

View on arXiv
Comments on this paper