Discrete Diffusion Probabilistic Models for Symbolic Music Generation

Autor:	Plasser, Matthias, Peter, Silvan, Widmer, Gerhard
Rok vydání:	2023
Předmět:	Computer Science - Sound Computer Science - Artificial Intelligence Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	Denoising Diffusion Probabilistic Models (DDPMs) have made great strides in generating high-quality samples in both discrete and continuous domains. However, Discrete DDPMs (D3PMs) have yet to be applied to the domain of Symbolic Music. This work presents the direct generation of Polyphonic Symbolic Music using D3PMs. Our model exhibits state-of-the-art sample quality, according to current quantitative evaluation metrics, and allows for flexible infilling at the note level. We further show, that our models are accessible to post-hoc classifier guidance, widening the scope of possible applications. However, we also cast a critical view on quantitative evaluation of music sample quality via statistical metrics, and present a simple algorithm that can confound our metrics with completely spurious, non-musical samples. Comment: In Proceedings of the 32nd International Joint Conference on Artificial Intelligence (IJCAI-23), Macau, China
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2305.09489 Zobrazit plný text záznamu View this record from Arxiv