{"ID":2869899,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.14052","arxiv_id":"2509.14052","title":"AnyAccomp: Generalizable Accompaniment Generation via Quantized Melodic Bottleneck","abstract":"Singing Accompaniment Generation (SAG) is the process of generating instrumental music for a given clean vocal input. However, existing SAG techniques use source-separated vocals as input and overfit to separation artifacts. This creates a critical train-test mismatch, leading to failure on clean, real-world vocal inputs. We introduce AnyAccomp, a framework that resolves this by decoupling accompaniment generation from source-dependent artifacts. AnyAccomp first employs a quantized melodic bottleneck, using a chromagram and a VQ-VAE to extract a discrete and timbre-invariant representation of the core melody. A subsequent flow-matching model then generates the accompaniment conditioned on these robust codes. Experiments show AnyAccomp achieves competitive performance on separated-vocal benchmarks while significantly outperforming baselines on generalization test sets of clean studio vocals and, notably, solo instrumental tracks. This demonstrates a qualitative leap in generalization, enabling robust accompaniment for instruments - a task where existing models completely fail - and paving the way for more versatile music co-creation tools. Demo audio and code: https://anyaccomp.github.io","short_abstract":"Singing Accompaniment Generation (SAG) is the process of generating instrumental music for a given clean vocal input. However, existing SAG techniques use source-separated vocals as input and overfit to separation artifacts. This creates a critical train-test mismatch, leading to failure on clean, real-world vocal inpu...","url_abs":"https://arxiv.org/abs/2509.14052","url_pdf":"https://arxiv.org/pdf/2509.14052v1","authors":"[\"Junan Zhang\",\"Yunjia Zhang\",\"Xueyao Zhang\",\"Zhizheng Wu\"]","published":"2025-09-17T14:55:21Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"eess.SP\"]","methods":"[\"Variational Autoencoder\"]","has_code":false}