AUTOMATIC DJ TRANSITIONS WITH DIFFERENTIABLE AUDIO EFFECTS AND GENERATIVE ADVERSARIAL NETWORKS

Chen, Bo YuBo YuChenHsu, Wei HanWei HanHsuLiao, Wei HsiangWei HsiangLiaoMartínez Ramírez, Marco A.Marco A.Martínez RamírezMitsufuji, YukiYukiMitsufujiYI-HSUAN YANG2023-10-062023-10-062022-01-01978166540540915206149https://scholars.lib.ntu.edu.tw/handle/123456789/635983A central task of a Disc Jockey (DJ) is to create a mixset of music with seamless transitions between adjacent tracks. In this paper, we explore a data-driven approach that uses a generative adversarial network to create the song transition by learning from real-world DJ mixes. The generator uses two differentiable digital signal processing components, an equalizer (EQ) and a fader, to mix two tracks selected by a data generation pipeline. The generator has to set the parameters of the EQs and fader in such a way that the resulting mix resembles real mixes created by human DJ, as judged by the discriminator counterpart. Result of a listening test shows that the model can achieve competitive results compared with a number of baselines.audio effects | deep learning | differentiable signal processing | DJ mix | generative adversarial network[SDGs]SDG10AUTOMATIC DJ TRANSITIONS WITH DIFFERENTIABLE AUDIO EFFECTS AND GENERATIVE ADVERSARIAL NETWORKSconference paper10.1109/ICASSP43922.2022.97466632-s2.0-85131242881https://api.elsevier.com/content/abstract/scopus_id/85131242881