# Audio Caption: Listen and Tell

## TL;DR

This paper introduces a new Mandarin-annotated dataset for audio captioning, aiming to enable automatic natural language descriptions of audio scenes and bridge the gap between audio perception and image captioning.

## Contribution

It provides the first manually-annotated audio caption dataset in Mandarin with English translations and baseline models for both languages.

## Key findings

- Baseline models achieve comparable BLEU scores in Mandarin and English.
- The dataset enables the development of audio captioning systems.
- Models generate understandable, data-related audio descriptions.

## Abstract

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.