← Back to all news
arXiv Machine Learning By Taejun Kim, Wonil Kim, Jongmin Jung, Hyeongseok Wi, Sangeun Kum, Keunhyoung Luke Kim, Taehyoung Kim, Dongjoo Moon, Seungsoon Park, Taewan Kim, Virginie Berger, Juhan Nam, Jongpil Lee

Tracing Inputs, Verifying Outputs: Validating Attribution in Music Generation

Read the original on arXiv Machine Learning →

The paper presents a method for attributing AI-generated music to its source audio inputs. By conditioning a music generator, MixAudio, solely on audio and tracing the inputs behind each output, the authors demonstrate that generated stems follow the timbre of the prompt audio and the harmony of the context audio. They also audit memorization with a musical version identification model, musicDNA, finding few reproductions outside the input records and achieving higher precision and recall than other detectors in human-judged cases.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
4d ago

A Tutorial on Generative Models for Music Audio

A tutorial monograph on generative models for music audio covers a wide range of applications—from instrumental clips and full songs with vocals to edits of existing recordings and real‑time accompaniment systems. It explains neural audio codecs, autoencoders, autoregressive and masked token models, diffusion and flow matching, sampling acceleration, and preference optimization, linking training objectives to published systems through worked examples. The book also discusses musical requirements for different tasks, compares representations and methods, and addresses evaluation, data provenance, memorization, attribution, and legal implications.

By Mateusz Modrzejewski, Joanna Kurkowska, Dorien Herremans
diffusion
More like this →
arXiv Machine Learning
Oct 3

TrueMuse: A Benchmark for Data Attribution in Text-to-Music Models

TrueMuse is a new benchmark designed to evaluate data attribution in text-to-music models. It consists of a controlled dataset created by fine‑tuning three diffusion‑based models on curated attribution samples, providing known attribution targets. The benchmark covers four settings—melodic structure, timbral characteristics, artist‑level style, and genre‑level patterns—across 133 attributes, 648 models, and 95,456 generated samples, and is used to assess existing black‑box attribution methods along several dimensions.

By Jiawei Yu, Jian Liu
diffusionfine-tuningbenchmarks
More like this →