Music Foundation Model as Generic Booster for Music Downstream Tasks

WeiHsiang Liao

Yuhta Takida

Yukara Ikemiya

Zhi Zhong*

Chieh-Hsin Lai

Giorgio Fabbro*

Kazuki Shimada

Keisuke Toyama*

Kinwai Cheuk

Marco A. Martínez-Ramírez

Shusuke Takahashi*

Stefan Uhlich*

Taketo Akama*

Woosung Choi

Yuichiro Koyama*

Yuki Mitsufuji

* External authors

TMLR

2025

Abstract

We demonstrate the efficacy of using intermediate representations from a single foundation model to enhance various music downstream tasks. We introduce SoniDo, a music foundation model (MFM) designed to extract hierarchical features from target music samples. By leveraging hierarchical intermediate features, SoniDo constrains the information granularity, leading to improved performance across various downstream tasks including both understanding and generative tasks. We specifically evaluated this approach on representative tasks such as music tagging, music transcription, music source separation, and music mixing. Our results reveal that the features extracted from foundation models provide valuable enhancements in training downstream task models. This highlights the capability of using features extracted from music foundation models as a booster for downstream tasks. Our approach not only benefits existing task-specific models but also supports music downstream tasks constrained by data scarcity. This paves the way for more effective and accessible music processing solutions.
Submission Length: Regular submission (no more than 12 pages of main content)