

















Abstract:Computational Music Generation is evolving towards non-conventional styles, demanding methods that enable precise and controllable blending of diverse music elements. In this work, we present a method for fine grained control using inference-time interventions on an autoregressive generative transformer, MusicGen. Through our approach, we achieve genre control by steering the residual stream using weights of a linear probe on it. By framing activation steering as a human-controllable interaction, our work highlights how interpretable model behaviors can empower in co-creative music this http URL samples demonstrating our method are available on our demo page.
| Subjects: | Sound (cs.SD); Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS) |
| Cite as: | arXiv:2506.10225 [cs.SD] |
| (or arXiv:2506.10225v2 [cs.SD] for this version) | |
| https://doi.org/10.48550/arXiv.2506.10225 arXiv-issued DOI via DataCite |
From: Swathi Shree Narashiman [view email]
[v1]
Wed, 11 Jun 2025 23:02:39 UTC (1,558 KB)
[v2]
Tue, 26 May 2026 09:48:50 UTC (136 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。