The AI community has made significant strides in developing powerful
foundation models, driven by large-scale multimodal datasets. However, in the
audio representation learning community, the present audio-language datasets
suffer from limitations such as insufficient volume, simplistic content, and
arduous collection procedures. To tackle these challenges, we present an
innovative and automatic audio caption generation pipeline based on a series of
public tools or APIs, and construct a large-scale, high-quality, audio-language
dataset, named as Auto-ACD, comprising over 1.9M audio-text pairs. To
demonstrate the effectiveness of the proposed dataset, we train popular models
on our dataset and show performance improvement on various downstream tasks,
namely, audio-language retrieval, audio captioning, environment classification.
In addition, we establish a novel test set and provide a benchmark for
audio-text tasks. The proposed dataset will be released at
this https URL

我们提出了一种基于公共工具或 API 的创新型自动音频说明生成流程，并构建了一个大规模、高质量的音频语言数据集 Auto-ACD，其中包含超过 190 万个音频文本对。通过在我们的数据集上训练流行模型并展示在各种下游任务（包括音频语言检索、音频说明和环境分类）上的性能改进，证明了所提出数据集的有效性。此外，我们建立了一个新颖的测试集，并为音频文本任务提供了一个基准。该数据集将在此 https URL 上发布。