Improving AI-generated music with user-guided training

TL;DR

This paper introduces a human-in-the-loop training method for AI music generation, using user feedback and genetic algorithms to iteratively improve music quality and personalization.

Contribution

It presents a novel approach combining user ratings and genetic algorithms to fine-tune AI music models based on subjective user preferences.

Findings

Average rating increased by 0.2 after first iteration

Second iteration added an increase of 0.39 in ratings

Demonstrates iterative improvement in user satisfaction

Abstract

AI music generation has advanced rapidly, with models like diffusion and autoregressive algorithms enabling high-fidelity outputs. These tools can alter styles, mix instruments, or isolate them. Since sound can be visualized as spectrograms, image-generation algorithms can be applied to generate novel music. However, these algorithms are typically trained on fixed datasets, which makes it challenging for them to interpret and respond to user input accurately. This is especially problematic because music is highly subjective and requires a level of personalization that image generation does not provide. In this work, we propose a human-computation approach to gradually improve the performance of these algorithms based on user interactions. The human-computation element involves aggregating and selecting user ratings to use as the loss function for fine-tuning the model. We employ a genetic algorithm that incorporates user feedback to enhance the baseline performance of a model initially trained on a fixed dataset. The effectiveness of this approach is measured by the average increase in user ratings with each iteration. In the pilot test, the first iteration showed an average rating increase of 0.2 compared to the baseline. The second iteration further improved upon this, achieving an additional increase of 0.39 over the first iteration.