English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Automated Audio captioning (AAC) is a cross-modal task that generates naturallanguage to describe the content of input audio. Most prior works usuallyextract single-modality acoustic features and are therefore sub-optimal for thecross-modal decoding task. In this work, we propose a novel AAC system calledCLIP-AAC to learn interactive cross-modality representation with both acousticand textual information. Specifically, the proposed CLIP-AAC introduces anaudio-head and a text-head in the pre-trained encoder to extract audio-textinformation. Furthermore, we also apply contrastive learning to narrow thedomain difference by learning the correspondence between the audio signal andits paired captions. Experimental results show that the proposed CLIP-AACapproach surpasses the best baseline by a significant margin on the Clothodataset in terms of NLP evaluation metrics. The ablation study indicates thatboth the pre-trained model and contrastive learning contribute to theperformance gain of the AAC model.

Interactive Audio-text Representation for Automated Audio Captioning with Contrastive Learning