Automated audio captioning: an overview of recent progress and new challenges

Automated audio captioning is a cross-modal translation task that aims to generate natural language descriptions for given clips. This has received increasing attention with the release of freely available datasets in recent years. The problem been addressed predominantly deep learning techniques. Numerous approaches have proposed, such as investigating different neural network architectures, exploiting auxiliary information keywords or sentence guide caption generation, and employing training strategies, which greatly facilitated development this field. In paper, we present comprehensive review published contributions automated captioning, from variety existing evaluation metrics datasets. We also discuss open challenges envisage possible future research directions.