arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.14712eess.AS
收藏

多标签音频分类:带噪声零样本教师模型

Multi-label audio classification with a noisy zero-shot teacher

Sebastian Braun, Hannes Gamper

AI总结:

本文提出一种结合自标签校正与数据增强的训练方案,利用零样本教师模型CLAP生成标签,提升复调音频检测的准确性与适应性,且模型高效适用于移动设备。

摘要:

我们提出了一种新颖的训练方案,结合自标签校正和数据增强方法,旨在处理噪声标签并提高复调音频内容检测任务在真实场景中的准确性。该增强方法通过混合多个音频片段并合并其标签来减少标签噪声,同时兼容多个活跃标签。我们进一步表明,使用同一预训练模型的自标签校正方法也能提升性能。最后,我们证明了利用诸如CLAP这样的强零样本模型为未标注数据生成标签是可行的,并可通过所提出的训练和标签增强方法改进结果。最终模型在性能上与CLAP相当,同时具备高效的移动设备友好架构,并能快速适应未标注的声音类别。

英文摘要:

We propose a novel training scheme using self-label correction and data augmentation methods designed to deal with noisy labels and improve real-world accuracy on a polyphonic audio content detection task. The augmentation method reduces label noise by mixing multiple audio clips and joining their labels, while being compatible with multiple active labels. We additionally show that performance can be improved by a self-label correction method using the same pretrained model. Finally, we show that it is feasible to use a strong zero-shot model such as CLAP to generate labels for unlabeled data and improve the results using the proposed training and label enhancement methods. The resulting model performs similar to CLAP while being an efficient mobile device friendly architecture and can be quickly adapted to unlabeled sound classes.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑