MUSEBENCH: A Benchmark for AI-Generated Music Detection and Artifact Analysis
University of Georgia（佐治亚大学）；College of Engineering（工程学院）；Virginia Commonwealth University（弗吉尼亚联邦大学）；University of Tennessee, Knoxville（田纳西大学诺克斯维尔分校）；Cornell University（康奈尔大学）
Yi Chen Liu, Syed Irfan Ali Meerza, Jiawei Yu, Xi Guo, Samuel Bright, Jian Liu
Advances in generative AI have made it possible to produce music that is nearly indistinguishable from human compositions, raising the question of whether such works can be reliably distinguished from human compositions. We present MUSEBENCH, a large-scale benchmark for AI-generated music detection and artifact analysis, comprising over 361K tracks. The dataset includes human compositions, stylistically matched music generated by ten state-of-the-art open-source and commercial models, such as Suno and Udio, as well as human-AI co-creations and variants processed with adversarial perturbations, compression, and acoustic post-processing. Using MUSEBENCH, we benchmark 11 automated detectors and evaluate their accuracy, generalization, and robustness, under default, out-of-domain, and transformed-variant experiment settings. We further conduct a comprehensive artifact analysis through acoustic feature inspection, identifying recurring signatures such as non-idiomatic harmonic progressions, upsampling induced spectral periodicities, and violations of physical performance constraints. Our findings reveal key strengths and vulnerabilities of existing detectors and provide practical insights for building more reliable AI music detection systems.
MSRBench: A Benchmarking Dataset for Music Source Restoration
Independent Researcher（独立研究者）；John Hopkins University（约翰·霍普金斯大学）；The Chinese University of Hong Kong（香港中文大学）；Sony AI（索尼人工智能）；King's College London（伦敦国王学院）
Upsampling artifacts are caused by problematic upsampling layers and due to spectral replicas that emerge while upsampling. Also, depending on the used upsampling layer, such artifacts can either be tonal artifacts (additive high-frequency noise) or filtering artifacts (substractive, attenuating some bands). In this work we investigate the practical implications of having upsampling artifacts in the resulting audio, by studying how different artifacts interact and assessing their impact on the models' performance. To that end, we benchmark a large set of upsampling layers for music source sepa…
Fraunhofer Institute for Integrated Circuits IIS（弗劳恩霍夫集成电路研究所）
Audio processing methods operating on a time-frequency representation of the signal can introduce unpleasant sounding artifacts known as musical noise. These artifacts are observed in the context of audio coding, speech enhancement, and source separation. The change in kurtosis of the power spectrum introduced during the processing was shown to correlate with the human perception of musical noise in the context of speech enhancement, leading to the proposal of measures based on it. These baseline measures are here shown to correlate with human perception only in a limited manner. As ground tru…
Vocoders are models capable of transforming a low-dimensional spectral representation of an audio signal, typically the mel spectrogram, to a waveform. Modern speech generation pipelines use a vocoder as their final component. Recent vocoder models developed for speech achieve a high degree of realism, such that it is natural to wonder how they would perform on music signals. Compared to speech, the heterogeneity and structure of the musical sound texture offers new challenges. In this work we focus on one specific artifact that some vocoder models designed for speech tend to exhibit when appl…
Instituto Superior Técnico, Universidade de Lisboa（里斯本大学高等技术学院）；INESC-ID Lisboa（里斯本信息与通信技术研究院）；Instituto Universitário de Lisboa (ISCTE-IUL)（里斯本大学学院（ISCTE-IUL））
Embodied cognition states that semantics is encoded in the brain as firing patterns of neural circuits, which are learned according to the statistical structure of human multimodal experience. However, each human brain is idiosyncratically biased, according to its subjective experience history, making this biological semantic machinery noisy with respect to the overall semantics inherent to media artifacts, such as music and language excerpts. We propose to represent shared semantics using low-dimensional vector embeddings by jointly modeling several brains from human subjects. We show these u…
Lightweight Self-Supervised Detection of Fundamental Frequency and Accurate Probability of Voicing in Monophonic Music
Dept. of Computer Science, Columbia University, New York, US（计算机科学系，哥伦比亚大学，纽约，美国）；Dept. of Mechanical Engineering and Dept. of Electrical Engineering, Columbia University（机械工程系和电气工程系，哥伦比亚大学）；Recognition Technologies, Inc., New York, US（识别技术公司，纽约，美国）
Cross-domain benchmarks reveal when coordinated AI agents improve scientific inference from partial evidence
Laboratory for Atomistic and Molecular Mechanics (LAMM)（原子分子力学实验室）；Department of Biological Engineering（生物工程系）；Department of Mechanical Engineering（机械工程系）；Department of Civil and Environmental Engineering（土木与环境工程系）；Center for Computational Science and Engineering, Schwarzman College of Computing（计算科学与工程中心）；Massachusetts Institute of Technology（麻省理工学院）
Melody or Machine: Detecting Synthetic Music with Dual-Stream Contrastive Learning
Indraprastha Institute of Information Technology Delhi (IIIT-Delhi)（印度理工学院德里分校）；Manipal University Jaipur（曼海姆大学斋普尔）；Netaji Subhas University of Technology (NSUT)（尼赫鲁大学技术学院）
