arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.15231cs.CLcs.AIcs.LG
收藏

跨语言与跨流派的合成歌词检测

Synthetic Lyrics Detection Across Languages and Genres

Deezer Research(Deepz研究)

Yanis Labrak, Markus Frohmann, Gabriel Meseguer-Brocal, Elena V. Epure

AI总结:

本研究构建多语言多流派歌词数据集,评估并适配合成文本检测方法至歌词,验证其在跨语言、少样本等场景下的泛化能力,为AI音乐政策提供依据。

摘要:

近年来,使用大型语言模型(LLM)生成音乐内容(尤其是歌词)的做法日益流行。这些进展为艺术家提供了宝贵的工具,并增强了他们的创作过程,但也引发了关于版权侵犯、消费者满意度和内容垃圾信息等方面的担忧。以往的研究已在多个领域探索了内容检测方法。然而,尚无工作聚焦于音乐中的文本模态——歌词。为填补这一空白,我们构建了一个包含多种语言、音乐流派和艺术家的真实与合成歌词的多样化数据集。生成流程经过了人工和自动化方法的双重验证。我们对现有合成文本检测方法在歌词这一此前未探索的数据类型上进行了全面评估。我们还研究了通过无监督域适应将表现最佳的特征适配到歌词的方法。结合音乐和工业界的约束,我们考察了这些方法在跨语言泛化、随数据可用性的扩展性、多语言内容处理以及少样本设置下对新流派的性能表现。我们的研究结果展现了令人鼓舞的前景,可为围绕AI生成音乐的政策决策提供参考,并增强对用户的透明度。

英文摘要:

In recent years, the use of large language models (LLMs) to generate music content, particularly lyrics, has gained in popularity. These advances provide valuable tools for artists and enhance their creative processes, but they also raise concerns about copyright violations, consumer satisfaction, and content spamming. Previous research has explored content detection in various domains. However, no work has focused on the text modality, lyrics, in music. To address this gap, we curated a diverse dataset of real and synthetic lyrics from multiple languages, music genres, and artists. The generation pipeline was validated using both humans and automated methods. We performed a thorough evaluation of existing synthetic text detection approaches on lyrics, a previously unexplored data type. We also investigated methods to adapt the best-performing features to lyrics through unsupervised domain adaptation. Following both music and industrial constraints, we examined how well these approaches generalize across languages, scale with data availability, handle multilingual language content, and perform on novel genres in few-shot settings. Our findings show promising results that could inform policy decisions around AI-generated music and enhance transparency for users.

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。

↑