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 this work, we propose to study the performance of a model trained with asentence embedding regression loss component for the Automated Audio Captioningtask. This task aims to build systems that can describe audio content with asingle sentence written in natural language. Most systems are trained with thestandard Cross-Entropy loss, which does not take into account the semanticcloseness of the sentence. We found that adding a sentence embedding loss termreduces overfitting, but also increased SPIDEr from 0.397 to 0.418 in our firstsetting on the AudioCaps corpus. When we increased the weight decay value, wefound our model to be much closer to the current state-of-the-art methods, witha SPIDEr score up to 0.444 compared to a 0.475 score. Moreover, this model useseight times less trainable parameters. In this training setting, the sentenceembedding loss has no more impact on the model performance.

Multitask learning in Audio Captioning: a sentence embedding regression loss acts as a regularizer