Search papers, labs, and topics across Lattice.
This paper introduces a novel approach for detecting AI-generated music in scenarios where the generating models are unknown, addressing the urgent need for synthetic content detection as user-friendly AI music services proliferate. The authors tackle two key tasks: discriminating real from synthetic music using a one-class method and performing zero-shot multi-class identification through unsupervised clustering. Their method combines artifact extraction with non-negative matrix factorization and classification techniques, achieving impressive performance that enables effective monitoring of large-scale music catalogs for AI-generated samples.
AI-generated music detection can now adapt in real-time to new generative models, achieving high accuracy without prior knowledge of the sources.
We present a novel method for AI-generated music detection in scenarios where the models that generated the input samples are unknown to the detector (e.g., from a newly released service). Since 2023, there has been a multiplication of user-friendly AI-music generation services (e.g., Suno, Udio), along with regular updates and new features. There is thus a need to address synthetic content detection in an unsupervised way to adapt to this rapidly changing context. This angle has not been much studied in music yet. We propose to study two tasks. First, discriminating between real and synthetic music. This may be approached in a one-class manner, namely, using some baseline real music and trying to determine what falls outside. Second, zero-shot multi-class identification, which is more similar to an unsupervised clustering task on a mix of real and various AI-music generations, where the goal is to create coherent, high-purity clusters. We propose a combination of a previously proposed artifact-extraction method, on top of which we apply non-negative matrix factorization and simple classification and clustering methods. We achieve excellent performance on both tasks, showing that the proposed methods may be used to monitor large-scale catalogs that may receive AI-generated samples from various newly released generative models.
