Audio Prompt Adapter: Unleashing Music Editing Abilities for Text-to-Music with Lightweight Finetuning

TL;DR

The paper introduces AP-Adapter, a lightweight module that enhances text-to-music models, enabling fine-grained music editing like genre and timbre transfer with minimal additional training.

Contribution

It presents a novel, low-parameter adapter that integrates with pretrained models to facilitate detailed music editing using audio and text inputs.

Findings

Effective in timbre and genre transfer tasks

Works well on out-of-domain audio with unseen instruments

Uses only 22M trainable parameters

Abstract

Text-to-music models allow users to generate nearly realistic musical audio with textual commands. However, editing music audios remains challenging due to the conflicting desiderata of performing fine-grained alterations on the audio while maintaining a simple user interface. To address this challenge, we propose Audio Prompt Adapter (or AP-Adapter), a lightweight addition to pretrained text-to-music models. We utilize AudioMAE to extract features from the input audio, and construct attention-based adapters to feedthese features into the internal layers of AudioLDM2, a diffusion-based text-to-music model. With 22M trainable parameters, AP-Adapter empowers users to harness both global (e.g., genre and timbre) and local (e.g., melody) aspects of music, using the original audio and a short text as inputs. Through objective and subjective studies, we evaluate AP-Adapter on three tasks: timbre transfer, genre transfer, and accompaniment generation. Additionally, we demonstrate its effectiveness on out-of-domain audios containing unseen instruments during training.