Music Style Transfer: A Position Paper

• DOI: 10.48550/arxiv.1803.06841
• Publication Date: 2018-01-01
• Authors: Shuqi Dai; Zheng Zhang; Gus Xia
• Keywords: Representation; Timbre

Led by the success of neural style transfer on visual arts, there has been a rising trend very recently in effort music transfer. However, "music style" is not yet well-defined concept from scientific point view. The difficulty lies intrinsic multi-level and multi-modal character representation (which different image representation). As result, depending their interpretation style", current studies under category transfer", are actually solving completely problems that belong to variety sub-fields Computer Music. Also, vanilla end-to-end approach, which aims at dealing with all levels once directly adopting method transfer, leads poor results. Thus, we vitally propose more scientifically-viable definition breaking it down into precise concepts timbre performance composition as well connect aspects existing well-established computer studies. In addition, discuss limitations modeling its future directions drawing spirit some deep generative models, especially ones using unsupervised learning disentanglement techniques.