# Investigating Personalization Methods in Text to Music Generation

arXiv: https://arxiv.org/abs/2309.11140 · HTML: https://mlsanity.com/paper/2309.11140/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 13 of its 21 references that are in the map.
- First posted on arXiv 20 Sep 2023.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 13 of 13)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [AudioLDM: Text-to-Audio Generation with Latent Diffusion Models](https://mlsanity.com/paper/2301.12503/) (2023)
- [Simple and Controllable Music Generation](https://mlsanity.com/paper/2306.05284/) (2023)
- [SVDiff: Compact Parameter Space for Diffusion Fine-Tuning](https://mlsanity.com/paper/2303.11305/) (2023)
- [Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models](https://mlsanity.com/paper/2302.12228/) (2023)
- [Key-Locked Rank One Editing for Text-to-Image Personalization](https://mlsanity.com/paper/2305.01644/) (2023)
- [Countering Language Drift via Visual Grounding](https://mlsanity.com/paper/1909.04499/) (2019)
- [Disentangled Multidimensional Metric Learning for Music Similarity](https://mlsanity.com/paper/2008.03720/) (2020)

## Built on by (most cited first, 11 of 11)

- [Zero-Shot Unsupervised and Text-Based Audio Editing Using DDPM Inversion](https://mlsanity.com/paper/2402.10009/) (2024)
- [Prompt-guided Precise Audio Editing with Diffusion Models](https://mlsanity.com/paper/2406.04350/) (2024)
- [FLUX that Plays Music](https://mlsanity.com/paper/2409.00587/) (2024)
- [Audio Prompt Adapter: Unleashing Music Editing Abilities for Text-to-Music with Lightweight Finetuning](https://mlsanity.com/paper/2407.16564/) (2024)
- [MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners](https://mlsanity.com/paper/2506.18729/) (2025)
- [MEDIC: Zero-shot Music Editing with Disentangled Inversion Control](https://mlsanity.com/paper/2407.13220/) (2024)
- [DRC: Enhancing Personalized Image Generation via Disentangled Representation Composition](https://mlsanity.com/paper/2504.17349/) (2025)
- [AudioMorphix: Training-free audio editing with diffusion probabilistic models](https://mlsanity.com/paper/2505.16076/) (2025)
- [Draw Your Mind: Personalized Generation via Condition-Level Modeling in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2508.03481/) (2025)
- [DreamAudio: Customized Text-to-Audio Generation with Diffusion Models](https://mlsanity.com/paper/2509.06027/) (2025)
- [EditGen: Harnessing Cross-Attention Control for Instruction-Based Auto-Regressive Audio Editing](https://mlsanity.com/paper/2507.11096/) (2025)

## Abstract (arXiv)

In this work, we investigate the personalization of text-to-music diffusion models in a few-shot setting. Motivated by recent advances in the computer vision domain, we are the first to explore the combination of pre-trained text-to-audio diffusers with two established personalization methods. We experiment with the effect of audio-specific data augmentation on the overall system performance and assess different training strategies. For evaluation, we construct a novel dataset with prompts and music clips. We consider both embedding-based and music-specific metrics for quantitative evaluation, as well as a user study for qualitative evaluation. Our analysis shows that similarity metrics are in accordance with user preferences and that current personalization approaches tend to learn rhythmic music constructs more easily than melody. The code, dataset, and example material of this study are open to the research community.