Genre Controlled Music Generation via Activation Steering

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Narashiman, Swathi, Mathur, Pranay, Panda, Dipanshu, Joe, Jayden Koshy, R, Harshith M, Veerakumar, Anish, Krishna, Aniruddh, A, Keerthiharan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918524239216640
author Narashiman, Swathi
Mathur, Pranay
Panda, Dipanshu
Joe, Jayden Koshy
R, Harshith M
Veerakumar, Anish
Krishna, Aniruddh
A, Keerthiharan
author_facet Narashiman, Swathi
Mathur, Pranay
Panda, Dipanshu
Joe, Jayden Koshy
R, Harshith M
Veerakumar, Anish
Krishna, Aniruddh
A, Keerthiharan
contents 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 generation.Audio samples demonstrating our method are available on our demo page.
format Preprint
id arxiv_https___arxiv_org_abs_2506_10225
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Genre Controlled Music Generation via Activation Steering
Narashiman, Swathi
Mathur, Pranay
Panda, Dipanshu
Joe, Jayden Koshy
R, Harshith M
Veerakumar, Anish
Krishna, Aniruddh
A, Keerthiharan
Sound
Artificial Intelligence
Audio and Speech Processing
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 generation.Audio samples demonstrating our method are available on our demo page.
title Genre Controlled Music Generation via Activation Steering
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2506.10225