Towards the Generation of Musical Explanations with GPT-3
Abstract
Open AI's language model, GPT-3, has shown great potential for many NLP tasks, with applications in many different domains. In this work we carry out a first study on GPT-3's capability to communicate musical decisions through textual explanations when prompted with a textual representation of a piece of music. Enabling a dialogue in human-AI music partnerships is an important step towards more engaging and creative human-AI interactions. Our results show that GPT-3 lacks the necessary intelligence to really understand musical decisions. A major barrier to reach a better performance is the lack of data that includes explanations of the creative process carried out by artists for musical pieces. We believe such a resource would aid the understanding and collaboration with AI music systems.
Keywords
Cite
@article{arxiv.2206.08264,
title = {Towards the Generation of Musical Explanations with GPT-3},
author = {Stephen James Krol and Maria Teresa Llano and Jon McCormack},
journal= {arXiv preprint arXiv:2206.08264},
year = {2022}
}