首页|Exploring Variational Auto-encoder Architectures,Configurations,and Datasets for Generative Music Explainable AI

Exploring Variational Auto-encoder Architectures,Configurations,and Datasets for Generative Music Explainable AI

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
Generative AI models for music and the arts in general are increasingly complex and hard to understand.The field of ex-plainable AI(XAI)seeks to make complex and opaque AI models such as neural networks more understandable to people.One ap-proach to making generative AI models more understandable is to impose a small number of semantically meaningful attributes on gen-erative AI models.This paper contributes a systematic examination of the impact that different combinations of variational auto-en-coder models(measureVAE and adversarialVAE),configurations of latent space in the AI model(from 4 to 256 latent dimensions),and training datasets(Irish folk,Turkish folk,classical,and pop)have on music generation performance when 2 or 4 meaningful musical at-tributes are imposed on the generative model.To date,there have been no systematic comparisons of such models at this level of com-binatorial detail.Our findings show that measureVAE has better reconstruction performance than adversarialVAE which has better musical attribute independence.Results demonstrate that measureVAE was able to generate music across music genres with inter-pretable musical dimensions of control,and performs best with low complexity music such as pop and rock.We recommend that a 32 or 64 latent dimensional space is optimal for 4 regularised dimensions when using measureVAE to generate music across genres.Our res-ults are the first detailed comparisons of configurations of state-of-the-art generative AI models for music and can be used to help select and configure AI models,musical features,and datasets for more understandable generation of music.

Variational auto-encoderexplainable AI(XAI)generative musicmusical featuresdatasets

Nick Bryan-Kinns、Bingyuan Zhang、Songyan Zhao、Berker Banar

展开 >

School of Electronic Engineering and Computer Science,Queen Mary University of London,London E1 4NS,UK

Computer Science Department,Carleton College,Northfield MN 55057,USA

UKRI Centre,UK,for Doctoral Training in Artificial Intelligence and Music supported by UKRIQueen Mary University of London,UK,and the Carleton College Career Center,USA for funding.Open Access funding provided by Queen

EP/S022694/1

2024

10.1007/s11633-023-1457-1

机器智能研究(英文)
中国科学院自动化所

机器智能研究(英文)

CSTPCDEI
影响因子：0.49
ISSN：2731-538X
年,卷(期)：2024.21(1)
  • 70