arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.04594cs.SDeess.AS
收藏

一种基于单事件声音的精细化音频-文本数据模拟流水线

A Detailed Audio-Text Data Simulation Pipeline using Single-Event Sounds

Shanghai Jiao Tong University(上海交通大学)

Xuenan Xu, Xiaohang Xu, Zeyu Xie, Pingyue Zhang, Mengyue Wu, Kai Yu

AI总结:

针对现有音频-文本数据集描述简单的问题,提出一种基于单事件声音的精细化音频-文本数据模拟流水线,从四维度控制音频细节并生成对应文本,验证了其助力模型学习精细化音频描述的有效性。

摘要:

近年来,音频-文本跨模态学习受到越来越多的关注。然而,现有大多数音频-文本数据集仅包含对声音事件的简单描述,与分类标签相比,这类描述的优势受到极大限制。本文首先分析了人类对音频的描述中,除声音事件标签外可能包含的精细化信息。基于该分析,我们提出了一种自动化流水线,用于构建具备丰富细节的音频-文本对。利用声音可在时域中混合与拼接的特性,我们在模拟混合音频时从四个维度控制细节:时间关系、响度、说话人身份和出现次数,并通过大语言模型将对应细节转换为描述文本,由此得到文本描述富含细节的音频-文本对。我们用少量模拟数据验证了该流水线的有效性,证明模拟数据可使模型学习到精细化的音频描述生成能力。

英文摘要:

Recently, there has been an increasing focus on audio-text cross-modal learning. However, most of the existing audio-text datasets contain only simple descriptions of sound events. Compared with classification labels, the advantages of such descriptions are significantly limited. In this paper, we first analyze the detailed information that human descriptions of audio may contain beyond sound event labels. Based on the analysis, we propose an automatic pipeline for curating audio-text pairs with rich details. Leveraging the property that sounds can be mixed and concatenated in the time domain, we control details in four aspects: temporal relationship, loudness, speaker identity, and occurrence number, in simulating audio mixtures. Corresponding details are transformed into captions by large language models. Audio-text pairs with rich details in text descriptions are thereby obtained. We validate the effectiveness of our pipeline with a small amount of simulated data, demonstrating that the simulated data enables models to learn detailed audio captioning.

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。

↑