Answers are grounded in this paper and cite their sources.
Modern streaming services dominate the way people consume music. While immediate access to music is certainly convenient, such services do not provide users with much control over their listening experience, other than simple volume settings or more rarely via equalization. In this work, we enhance the music listening experience by combining deep musical source separation with online binaural spatial audio remixing of the separated sources. We introduce YouMixIt 1 , an end-to-end web application that allows users to separate music downloaded from YouTube into four different audio stems (vocals, bass, drums, and accompaniment) and interactively manipulate the 3D position and volume settings of each stem within the simulated listening space. Our interface introduces novel degrees of control allowing users to create personalized musical mixtures.
No takes yet. Share an insight, caveat, or question.
Ophir et al. (2021) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: