Instruct-MusicGen: Unlocking Text-to-Music Editing for Music Language Models via Instruction Tuning

research work·research paper·active

Research work examining music/audio editing, text-to-music generation.

Verified facts

Official site	https://arxiv.org/abs/2405.18386 ↗
Geography	Global
arxiv	2405.18386
venue	Accepted at ISMIR 2025 Conference. Code and demo are available at: https://github.com/ldzhangyx/instruct-musicgen
authors	Yixiao Zhang; Yukara Ikemiya; Woosung Choi; Naoki Murata; Marco A. Martínez-Ramírez; Liwei Lin; Gus Xia; Wei-Hsiang Liao; Yuki Mitsufuji; Simon Dixon
methods	instruction tuning; language modeling
code urls	https://github.com/ldzhangyx/instruct-musicgen
demo urls	https://github.com/ldzhangyx/instruct-musicgen
exact title	Instruct-MusicGen: Unlocking Text-to-Music Editing for Music Language Models via Instruction Tuning
project urls	unknown
original title	unknown
citation counts	unknown
research topics	music/audio editing; text-to-music generation
peer review status	venue or acceptance claim recorded in arXiv comment
disclosed conflicts	unknown
stated contribution	Presents or evaluates the system, method, benchmark, or analysis identified in the paper title.
us market scope basis	Included as a materially relevant public research artifact in the US-facing AI-music ecosystem; direct affiliation varies.
funding acknowledgements	unknown
affiliations at publication	unknown
publication or preprint date	2024-05-28
abstract level neutral summary	The work studies music/audio editing, text-to-music generation; methods and evaluation details are in the official abstract.
datasets benchmarks models tools used	MusicGen
correction withdrawal retraction status	No withdrawal marker observed in captured arXiv metadata.