Paper ID: 2409.01201

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

Jaeyeon Kim, Minjeon Jeon, Jaeyoon Jung, Sang Hoon Woo, Jinjoo Lee

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.

Submitted: Sep 2, 2024