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.
LyricWhiz: Robust Multilingual Zero-shot Lyrics Transcription by Whispering to ChatGPT
Beihang University(北京航空航天大学);Beijing Academy of Artificial Intelligence(北京智源人工智能研究院);Carnegie Mellon University(卡内基梅隆大学);Hong Kong University of Science and Technology(香港科技大学);Queen Mary University of London(伦敦大学玛丽女王学院);University of Sheffield(谢菲尔德大学);University of Waterloo(滑铁卢大学)
LyricJam Sonic: A Generative System for Real-Time Composition and Musical Improvisation
University of Waterloo(滑铁卢大学)
电子音乐艺术家和声音设计师有独特的工作流程实践,需要专门的方法来开发音乐信息检索和创造力支持工具。此外,电子乐器,如模块化合成器,具有近乎无限的声音创作可能性,可以组合起来创建独特而复杂的音频路径。发现有趣声音的过程往往是偶然的,不可能复制。出于这个原因,许多电子流派的音乐家在录音室工作时一直录制音频输出。因此,艺术家很难从数千小时的录音中重新发现可能适合在他们的作品中使用的音频片段。在本文中,我们描述了LyricJam Sonic --一种新颖的创作工具,让音乐家重新发现他们以前的录音,将它们与其他录音重新联系起来,并在实时的【形】创作原创现场音乐作品。一种双模态AI驱动的方法使用生成的歌词线从艺术家过去的录音室录音中找到匹配的音频片段,并使用它们生成新的歌词线,这些歌词线又用于找到其他片段,从而创建一个连续和不断发展的音乐和歌词流。这样做的目的是让艺术家保持一种有利于音乐创作的创造性流动状态,而不是让他们进入一种故意搜索过去音频片段的分析/批判状态。该系统可以在没有用户输入的情况下以完全自主模式运行,或者以现场表演模式运行,其中艺术家播放现场音乐,而系统“收听”并创建连续的音乐和歌词流作为响应。
Contrastive Analysis of Linguistic Representations in Large Language Model Outputs through Structured Synthetic Data Generation and Abstracted N-gram Associations
AraGenre 2026: A Hierarchical Definition-Guided Arabic Genre Classification Shared Task
VinUniversity(温大);Lancaster University(兰卡斯特大学);King Fahd University of Petroleum and Minerals(法赫德国王石油与矿产大学);Onaizah Colleges(欧奈宰学院);University College of Applied Sciences(应用科学大学学院);Hamad Bin Khalifa University(哈马德·本·哈利法大学)
Cross-Genre Argument Mining: Can Language Models Automatically Fill in Missing Discourse Markers?
Laboratório de Inteligência Artificial e Ciência de Computadores (LIACC)(人工智能与计算机科学实验室(LIACC));Faculdade de Engenharia da Universidade do Porto(波尔图大学工程学院);Natural Language Learning Group (NLLG)(自然语言学习组(NLLG));Faculty of Technology, Bielefeld University(比勒费尔德大学技术学院)