English

EnCLAP++: Analyzing the EnCLAP Framework for Optimizing Automated Audio Captioning Performance

Audio and Speech Processing 2024-09-04 v1 Artificial Intelligence Sound

Abstract

In this work, we aim to analyze and optimize the EnCLAP framework, a state-of-the-art model in automated audio captioning. We investigate the impact of modifying the acoustic encoder components, explore pretraining with different dataset scales, and study the effectiveness of a reranking scheme. Through extensive experimentation and quantitative analysis of generated captions, we develop EnCLAP++, an enhanced version that significantly surpasses the original.

Keywords

Cite

@article{arxiv.2409.01201,
  title  = {EnCLAP++: Analyzing the EnCLAP Framework for Optimizing Automated Audio Captioning Performance},
  author = {Jaeyeon Kim and Minjeon Jeon and Jaeyoon Jung and Sang Hoon Woo and Jinjoo Lee},
  journal= {arXiv preprint arXiv:2409.01201},
  year   = {2024}
}

Comments

Accepted to DCASE2024 Workshop

R2 v1 2026-06-28T18:31:28.439Z