Recent advances in using language models to obtain cross-modal audio-text representations have overcome the limitations of conventional training approaches that use predefined labels. This has allowed the community to make progress in tasks like zero-shot classification, which would otherwise not be possible. However, learning such representations requires a large amount of human-annotated audio-text pairs. In this paper, we study unsupervised approaches to improve the learning framework of such representations with unpaired text and audio. We explore domain-unspecific and domain-specific curation methods to create audio-text pairs that we use to further improve the model. We also show that when domain-specific curation is used in conjunction with a soft-labeled contrastive loss, we are able to obtain significant improvement in terms of zero-shot classification performance on downstream sound event classification or acoustic scene classification tasks.

翻译：近年来，利用语言模型获取跨模态音频-文本表示的方法克服了传统基于预定义标签训练方法的局限性，使得在零样本分类等任务上取得了原本无法实现的进展。然而，学习此类表示需要大量人工标注的音频-文本对。本文研究了利用无标注文本和音频无监督改进此类表示学习框架的方法。我们探索了领域无关与领域特定的数据整理策略，以生成可用于进一步优化模型的音频-文本对。研究还表明，当领域特定的整理方法与软标签对比损失联合使用时，能够在下游声音事件分类或声学场景分类任务上显著提升零样本分类性能。