Multilingual audio-text retrieval (ML-ATR) is a challenging task that aims to retrieve audio clips or multilingual texts from databases. However, existing ML-ATR schemes suffer from inconsistencies for instance similarity matching across languages. We theoretically analyze the inconsistency in terms of both multilingual modal alignment direction error and weight error, and propose the theoretical weight error upper bound for quantifying the inconsistency. Based on the analysis of the weight error upper bound, we find that the inconsistency problem stems from the data distribution error caused by random sampling of languages. We propose a consistent ML-ATR scheme using 1-to-k contrastive learning and audio-English co-anchor contrastive learning, aiming to mitigate the negative impact of data distribution error on recall and consistency in ML-ATR. Experimental results on the translated AudioCaps and Clotho datasets show that our scheme achieves state-of-the-art performance on recall and consistency metrics for eight mainstream languages, including English. Our code will be available at https://github.com/ATRI-ACL/ATRI-ACL.

本研究针对多语音音频文本检索（ML-ATR）中的不一致性问题，特别是跨语言相似性匹配的挑战，进行理论分析并提出了一种新的解决方案。通过1-to-k对比学习和音频-英语共同锚对比学习，提出了一种一致的ML-ATR方案，有效缓解了数据分布错误对检索率和一致性的负面影响，实验结果表明该方案在多种主流语言上表现出色。

ATRI：通过减少数据分布错误来缓解多语音音频文本检索不一致性