arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.10684eess.AScs.SD
收藏

FakeMusicCaps:一个用于检测和归因经由文本到音乐模型生成的合成音乐的数据集

FakeMusicCaps: a Dataset for Detection and Attribution of Synthetic Music Generated via Text-to-Music Models

Politecnico di Milano(米兰理工大学)

Luca Comanducci, Paolo Bestagini, Stefano Tubaro

AI总结:

针对文本到音乐模型引发的版权与归因问题,本文提出数据集FakeMusicCaps,包含多种最先进TTM技术重新生成的音乐-字幕配对,并进行了音频检测与归因的初步评估实验。

摘要:

文本到音乐(Text-to-Music, TTM)模型近期彻底改变了自动音乐生成研究领域。具体而言,它们通过超越所有先前最先进模型的性能,并降低使用它们所需的技术水平。由于这些原因,它们已开始被广泛用于商业用途和音乐制作实践。TTM的这种广泛传播引发了关于版权侵犯和正当归因的诸多担忧,使得音频取证社区需要对其进行认真考虑。在本文中,我们解决了TTM生成数据的检测和归因问题。我们提出了一个数据集FakeMusicCaps,其中包含经由多种最先进TTM技术重新生成的音乐-字幕配对数据集MusicCaps的多个版本。我们通过进行关于TTM生成音频的检测和归因的初步实验,来评估所提出的数据集。

英文摘要:

Text-To-Music (TTM) models have recently revolutionized the automatic music generation research field. Specifically, by reaching superior performances to all previous state-of-the-art models and by lowering the technical proficiency needed to use them. Due to these reasons, they have readily started to be adopted for commercial uses and music production practices. This widespread diffusion of TTMs poses several concerns regarding copyright violation and rightful attribution, posing the need of serious consideration of them by the audio forensics community. In this paper, we tackle the problem of detection and attribution of TTM-generated data. We propose a dataset, FakeMusicCaps that contains several versions of the music-caption pairs dataset MusicCaps re-generated via several state-of-the-art TTM techniques. We evaluate the proposed dataset by performing initial experiments regarding the detection and attribution of TTM-generated audio.

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。

↑