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 https://auto-acd.github.io/.

翻译：人工智能社区在大规模多模态数据集的推动下，在开发强大基础模型方面取得了显著进展。然而，在音频表示学习领域，现有的音频-语言数据集存在数据量不足、内容单一、收集流程繁琐等局限。为应对这些挑战，我们提出了一种基于系列公开工具或API的创新性自动化音频描述生成流程，并构建了一个包含超过190万对音频-文本对的大规模高质量音频-语言数据集——Auto-ACD。为验证所提数据集的有效性，我们在该数据集上训练主流模型，并在音频-语言检索、音频描述生成、环境分类等多项下游任务中展示了性能提升。此外，我们构建了全新测试集，并建立了音频-文本任务的基准评测。该数据集将在https://auto-acd.github.io/ 公开发布。