Back to list

Computer-assisted manual segmentation of music recordings: An on-the-fly approach to ‘Sample’-selection for music production

Authors Rothmund, F.
Year 2017
Thesis Type Audio Engineering project
Topic Audio Signal Processing
Keywords Music Information Retrieval, signal processing
Abstract The goal of this project was to develop a tool that allows musicians to easily select interesting parts of a music recording during playback in order to rearrange them for new compositions. The manual selection and cropping of so called samples can be a tedious and often uninspiring task. This project aims to develop a way to select interesting parts in a recording more efficiently and intuitively: While the user listens to a music recording, he or she marks interesting parts by pressing a key or switch. The computer then corrects the timing to select the parts that the user intended to select and that make sense musically. The underlying algorithm considers the rhythmic structure of the musical piece, as well as the user’s timing.
Supervisors Sontacchi, A.