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

Automated audio captioning aims to use natural language to describe thecontent of audio data. This paper presents an audio captioning system with anencoder-decoder architecture, where the decoder predicts words based on audiofeatures extracted by the encoder. To improve the proposed system, transferlearning from either an upstream audio-related task or a large in-domaindataset is introduced to mitigate the problem induced by data scarcity.Besides, evaluation metrics are incorporated into the optimization of the modelwith reinforcement learning, which helps address the problem of ``exposurebias'' induced by ``teacher forcing'' training strategy and the mismatchbetween the evaluation metrics and the loss function. The resulting system wasranked 3rd in DCASE 2021 Task 6. Ablation studies are carried out toinvestigate how much each element in the proposed system can contribute tofinal performance. The results show that the proposed techniques significantlyimprove the scores of the evaluation metrics, however, reinforcement learningmay impact adversely on the quality of the generated captions.

An Encoder-Decoder Based Audio Captioning System With Transfer and Reinforcement Learning