Published On: Wed, Jun 22nd, 2022

Towards the Generation of Musical Explanations with GPT-3


Human-machine collaboration is an interesting field in the development of creative systems. It would be ideal if the system could produce novel creative outputs, explain them and discuss them with their contributors. A recent paper on arXiv.org presents a study on the generation of explanations of musical decisions made by AI music systems.

Music editing equipment. Image credit: francos via Pxhere, CC0 Public Domain

Music editing equipment. Image credit: francos via Pxhere, CC0 Public Domain

Researchers leverage the capabilities of transformer-based technologies to generate explanations of musical decisions using GPT-3, a state-of-the-art natural language model. It was fed with example pieces of the music with explanations provided by the author. Then, the capability to produce explanations itself was tested.

The experiments show that, in this context, GPT-3’s few-shot learning capabilities are still limited. It can express explanations about musical notation but lacks the necessary intelligence to really understand it. Researchers conclude that fine-tuning the model on musical explanations is needed.

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.

Research article: Krol, S. J., Llano, M. T., and McCormack, J., “Towards the Generation of Musical Explanations with GPT-3”, 2022. Link: https://arxiv.org/abs/2206.08264




Source link

Most Popular News

Local Business Directory, Search Engine Submission & SEO Tools