Versatile Symbolic Music-for-Music Modeling via Function Alignment

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Jiang, Junyan, Chin, Daniel, Lin, Liwei, Liu, Xuanjie, Xia, Gus
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908562563792896
author Jiang, Junyan
Chin, Daniel
Lin, Liwei
Liu, Xuanjie
Xia, Gus
author_facet Jiang, Junyan
Chin, Daniel
Lin, Liwei
Liu, Xuanjie
Xia, Gus
contents Many music AI models learn a map between music content and human-defined labels. However, many annotations, such as chords, can be naturally expressed within the music modality itself, e.g., as sequences of symbolic notes. This observation enables both understanding tasks (e.g., chord recognition) and conditional generation tasks (e.g., chord-conditioned melody generation) to be unified under a music-for-music sequence modeling paradigm. In this work, we propose parameter-efficient solutions for a variety of symbolic music-for-music tasks. The high-level idea is that (1) we utilize a pretrained Language Model (LM) for both the reference and the target sequence and (2) we link these two LMs via a lightweight adapter. Experiments show that our method achieves superior performance among different tasks such as chord recognition, melody generation, and drum track generation. All demos, code and model weights are publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2506_15548
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Versatile Symbolic Music-for-Music Modeling via Function Alignment
Jiang, Junyan
Chin, Daniel
Lin, Liwei
Liu, Xuanjie
Xia, Gus
Sound
Many music AI models learn a map between music content and human-defined labels. However, many annotations, such as chords, can be naturally expressed within the music modality itself, e.g., as sequences of symbolic notes. This observation enables both understanding tasks (e.g., chord recognition) and conditional generation tasks (e.g., chord-conditioned melody generation) to be unified under a music-for-music sequence modeling paradigm. In this work, we propose parameter-efficient solutions for a variety of symbolic music-for-music tasks. The high-level idea is that (1) we utilize a pretrained Language Model (LM) for both the reference and the target sequence and (2) we link these two LMs via a lightweight adapter. Experiments show that our method achieves superior performance among different tasks such as chord recognition, melody generation, and drum track generation. All demos, code and model weights are publicly available.
title Versatile Symbolic Music-for-Music Modeling via Function Alignment
topic Sound
url https://arxiv.org/abs/2506.15548