Expanding on EnCLAP with Auxiliary Retrieval Model for Automated Audio Captioning
This work addresses audio captioning and retrieval challenges for the DCASE2024 community, but it is incremental as it builds on an existing framework.
The authors tackled automated audio captioning and language-based audio retrieval by extending the EnCLAP framework with modifications and a reranking process, achieving an FENSE score of 0.542 on Task6 and an mAP@10 score of 0.386 on Task8, which significantly outperformed baselines.
In this technical report, we describe our submission to DCASE2024 Challenge Task6 (Automated Audio Captioning) and Task8 (Language-based Audio Retrieval). We develop our approach building upon the EnCLAP audio captioning framework and optimizing it for Task6 of the challenge. Notably, we outline the changes in the underlying components and the incorporation of the reranking process. Additionally, we submit a supplementary retriever model, a byproduct of our modified framework, to Task8. Our proposed systems achieve FENSE score of 0.542 on Task6 and mAP@10 score of 0.386 on Task8, significantly outperforming the baseline models.