JEN-1 DreamStyler: Customized Musical Concept Learning via Pivotal Parameters Tuning

TL;DR

This paper introduces Jen1-DreamStyler, a novel method for customized text-to-music generation that captures specific concepts from reference music using pivotal parameter tuning, addressing overfitting and concept conflict issues.

Contribution

It presents a new approach for personalized music generation from reference music, including a concept enhancement strategy and a new dataset for evaluation.

Findings

Outperforms baseline models in qualitative and quantitative tests

Effectively captures and combines multiple musical concepts

Addresses overfitting through pivotal parameter tuning

Abstract

Large models for text-to-music generation have achieved significant progress, facilitating the creation of high-quality and varied musical compositions from provided text prompts. However, input text prompts may not precisely capture user requirements, particularly when the objective is to generate music that embodies a specific concept derived from a designated reference collection. In this paper, we propose a novel method for customized text-to-music generation, which can capture the concept from a two-minute reference music and generate a new piece of music conforming to the concept. We achieve this by fine-tuning a pretrained text-to-music model using the reference music. However, directly fine-tuning all parameters leads to overfitting issues. To address this problem, we propose a Pivotal Parameters Tuning method that enables the model to assimilate the new concept while preserving its original generative capabilities. Additionally, we identify a potential concept conflict when introducing multiple concepts into the pretrained model. We present a concept enhancement strategy to distinguish multiple concepts, enabling the fine-tuned model to generate music incorporating either individual or multiple concepts simultaneously. Since we are the first to work on the customized music generation task, we also introduce a new dataset and evaluation protocol for the new task. Our proposed Jen1-DreamStyler outperforms several baselines in both qualitative and quantitative evaluations. Demos will be available at https://www.jenmusic.ai/research#DreamStyler.