English

GD-Retriever: Controllable Generative Text-Music Retrieval with Diffusion Models

Sound 2025-06-25 v2 Audio and Speech Processing

Abstract

Multimodal contrastive models have achieved strong performance in text-audio retrieval and zero-shot settings, but improving joint embedding spaces remains an active research area. Less attention has been given to making these systems controllable and interactive for users. In text-music retrieval, the ambiguity of freeform language creates a many-to-many mapping, often resulting in inflexible or unsatisfying results. We introduce Generative Diffusion Retriever (GDR), a novel framework that leverages diffusion models to generate queries in a retrieval-optimized latent space. This enables controllability through generative tools such as negative prompting and denoising diffusion implicit models (DDIM) inversion, opening a new direction in retrieval control. GDR improves retrieval performance over contrastive teacher models and supports retrieval in audio-only latent spaces using non-jointly trained encoders. Finally, we demonstrate that GDR enables effective post-hoc manipulation of retrieval behavior, enhancing interactive control for text-music retrieval tasks.

Keywords

Cite

@article{arxiv.2506.17886,
  title  = {GD-Retriever: Controllable Generative Text-Music Retrieval with Diffusion Models},
  author = {Julien Guinot and Elio Quinton and György Fazekas},
  journal= {arXiv preprint arXiv:2506.17886},
  year   = {2025}
}

Comments

Accepted to ISMIR 2025

R2 v1 2026-07-01T03:28:08.518Z