Audio Caption: Listen and Tell
This work addresses the gap in machine perception for audio captioning, enabling automated scene description, but it is incremental as it adapts existing methods to a new domain with a new dataset.
The paper tackles the problem of generating natural language descriptions for audio scenes, which is underexplored compared to image captioning, by introducing a manually-annotated dataset in Mandarin with English translations and providing a baseline encoder-decoder model that achieves similar BLEU scores for both languages, producing understandable captions.
Increasing amount of research has shed light on machine perception of audio events, most of which concerns detection and classification tasks. However, human-like perception of audio scenes involves not only detecting and classifying audio sounds, but also summarizing the relationship between different audio events. Comparable research such as image caption has been conducted, yet the audio field is still quite barren. This paper introduces a manually-annotated dataset for audio caption. The purpose is to automatically generate natural sentences for audio scene description and to bridge the gap between machine perception of audio and image. The whole dataset is labelled in Mandarin and we also include translated English annotations. A baseline encoder-decoder model is provided for both English and Mandarin. Similar BLEU scores are derived for both languages: our model can generate understandable and data-related captions based on the dataset.