Abstract
Variational Autoencoders(VAEs) have already achieved great results on image generation and recently made promising progress on music generation. However, the generation process is still quite difficult to control in the sense that the learned latent representations lack meaningful music semantics. It would be much more useful if people can modify certain music features, such as rhythm and pitch contour, via latent representations to test different composition ideas. In this paper, we propose a new method to inspect the pitch and rhythm interpretations of the latent representations and we name it disentanglement by augmentation. Based on the interpretable representations, an intuitive graphical user interface is designed for users to better direct the music creation process by manipulating the pitch contours and rhythmic complexity.
Abstract (translated)
变分自动编码器(VAES)在图像生成方面已经取得了很大的进展,在音乐生成方面也取得了很大的进展。然而,从所学的潜在表征缺乏有意义的音乐语义学的意义上来说,生成过程仍然很难控制。如果人们可以通过潜在的表现来测试不同的构图思想,从而改变某些音乐特征,如节奏和音高轮廓,那将是非常有用的。本文提出了一种新的检测潜在表征的音高和节奏解释的方法,并将其命名为增广分离法。基于可解释的表现形式,设计了一个直观的图形用户界面,用户可以通过操纵音高轮廓和节奏复杂度来更好地指导音乐创作过程。
URL
https://arxiv.org/abs/1904.08842