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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In recent years, datasets of paired audio and captions have enabledremarkable success in automatically generating descriptions for audio clips,namely Automated Audio Captioning (AAC). However, it is labor-intensive andtime-consuming to collect a sufficient number of paired audio and captions.Motivated by the recent advances in Contrastive Language-Audio Pretraining(CLAP), we propose a weakly-supervised approach to train an AAC model assumingonly text data and a pre-trained CLAP model, alleviating the need for pairedtarget data. Our approach leverages the similarity between audio and textembeddings in CLAP. During training, we learn to reconstruct the text from theCLAP text embedding, and during inference, we decode using the audioembeddings. To mitigate the modality gap between the audio and text embeddingswe employ strategies to bridge the gap during training and inference stages. Weevaluate our proposed method on Clotho and AudioCaps datasets demonstrating itsability to achieve a relative performance of up to ~$83\%$ compared to fullysupervised approaches trained with paired target data.

Weakly-supervised Automated Audio Captioning via text only training