Computer Evaluation Of Musical Timbre Transfer On Drum Tracks

Musical timbre transfer is the task of re-rendering the musical content of a given source using the rendering style of a target sound, this task is sometimes also called interpretation. The source keeps its musical content, e.g., pitch, microtiming, orchestration, and syncopation. We specifically focus on the task of transferring the style of percussive patterns extracted from polyphonic audio using a MelGAN-VC model (Pasini, 2019) by training acoustic properties for each genre. Evaluating audio style transfer is challenging and typically requires user studies. We propose an analytical methodology based on supervised and unsupervised learning including visualization for evaluating musical timbre transfer that can be used instead of, or in addition to, user studies. The proposed methodology is used to evaluate the MelGAN-VC model for musical timbre transfer of drum tracks