arXiv AI August 6, 2026 By Alon Ziv, Harel Pogoda, Yossi Adi

InvFlowFD: Reference-Free and Background-Set-Free Perceptual Music Quality Metric with Flow Matching Inversion

arXiv:2608. 04142v1 Announce Type: cross Abstract: Existing reference-free methods for evaluating music perceptual quality alleviate the need for paired noisy-clean data, but they still rely on a background set, which is used to compute aggregated statistics of clean audio samples.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

diffusion

arXiv AI

1d ago

Distinguishing AI-Generated Music from Edited Audio as a Hard-Negative Robustness Task

arXiv:2608. 14916v1 Announce Type: cross Abstract: AI-generated music detectors are commonly evaluated against original songs, but real-world uploads are often remixed, re-encoded, pitch-shifted, or otherwise edited.

By Alexandru-Stefan Morosanu, Valerian Cecan, Stefan-Daniel Achirei, Laura Erhan

llms

arXiv Machine Learning

Jun 26

Conditional Flow Matching for Visually-Guided Acoustic Highlighting

arXiv:2602. 03762v4 Announce Type: replace-cross Abstract: Visually-guided acoustic highlighting seeks to rebalance audio in alignment with the accompanying video, creating a coherent audio-visual experience.

By Hugo Malard, Gael Le Lan, Daniel Wong, David Lou Alon, Yi-Chiao Wu, Sanjeel Parekh

diffusion multimodal benchmarks safety

arXiv Machine Learning

1d ago

What Makes a Good Layer? Assessing the Layer-Wise Intrinsic Properties of Music Foundation Models

arXiv:2608. 14819v1 Announce Type: cross Abstract: Music foundation models are commonly used as frozen audio feature extractors, yet selecting which layer to extract from remains largely heuristic.

By Angelos-Nikolaos Kanatas, Yuexuan Kong, Pablo Alonso-Jim\'enez, Xavier Serra, Dmitry Bogdanov

arXiv AI

Jul 10

Echoes: A semantically-aligned music deepfake detection dataset

arXiv:2603. 23667v2 Announce Type: replace-cross Abstract: We introduce Echoes, a new dataset for music deepfake detection designed for training and benchmarking detectors under realistic and provider-diverse conditions.

By Octavian Pascu, Dan Oneata, Horia Cucu, Nicolas M. Muller

benchmarks safety

arXiv Machine Learning

Jun 16

Beyond Artifacts: Towards Generalizable Synthetic Song Detection via Music-Intrinsic Features

arXiv:2606. 16612v1 Announce Type: cross Abstract: The rapid advancement of AI music generators highlights the urgent need for reliable Synthetic Song Detection (SSD).

By Yan Han, Zhibin Wen, Yuan Wang, Shuangrun Shao, Xiaobing Li, Yang Xu, Wei Li

benchmarks

arXiv Machine Learning

Jul 31

Integrating Contextual Embeddings into Evaluation of Expressive MIDI Piano Performances

arXiv:2607. 27909v1 Announce Type: cross Abstract: Objective evaluation of expressive MIDI piano performances typically relies on attribute statistics such as timing, velocity, and duration of individual notes.

By Dmitrii Gavrilev, Ilya Borovik, Vladimir Viro

rag safety

Related stories

Distinguishing AI-Generated Music from Edited Audio as a Hard-Negative Robustness Task

Conditional Flow Matching for Visually-Guided Acoustic Highlighting

What Makes a Good Layer? Assessing the Layer-Wise Intrinsic Properties of Music Foundation Models

Echoes: A semantically-aligned music deepfake detection dataset

Beyond Artifacts: Towards Generalizable Synthetic Song Detection via Music-Intrinsic Features

Integrating Contextual Embeddings into Evaluation of Expressive MIDI Piano Performances