English

In-Context Prompt Editing For Conditional Audio Generation

Sound 2023-11-03 v1 Computation and Language Audio and Speech Processing

Abstract

Distributional shift is a central challenge in the deployment of machine learning models as they can be ill-equipped for real-world data. This is particularly evident in text-to-audio generation where the encoded representations are easily undermined by unseen prompts, which leads to the degradation of generated audio -- the limited set of the text-audio pairs remains inadequate for conditional audio generation in the wild as user prompts are under-specified. In particular, we observe a consistent audio quality degradation in generated audio samples with user prompts, as opposed to training set prompts. To this end, we present a retrieval-based in-context prompt editing framework that leverages the training captions as demonstrative exemplars to revisit the user prompts. We show that the framework enhanced the audio quality across the set of collected user prompts, which were edited with reference to the training captions as exemplars.

Keywords

Cite

@article{arxiv.2311.00895,
  title  = {In-Context Prompt Editing For Conditional Audio Generation},
  author = {Ernie Chang and Pin-Jie Lin and Yang Li and Sidd Srinivasan and Gael Le Lan and David Kant and Yangyang Shi and Forrest Iandola and Vikas Chandra},
  journal= {arXiv preprint arXiv:2311.00895},
  year   = {2023}
}

Comments

5 pages, 3 figures, 2 tables

R2 v1 2026-06-28T13:09:09.095Z