Princeton University users: to view a senior thesis while away from campus, connect to the campus network via the Global Protect virtual private network (VPN). Unaffiliated researchers: please note that requests for copies are handled manually by staff and require time to process.
 

Publication:

noVox: A Music Source Separation tool for Generating Non-Explicit Lyrics

Loading...
Thumbnail Image

Files

aa6162_written_final_report-6.pdf (996.28 KB)

Date

2025

Journal Title

Journal ISSN

Volume Title

Publisher

Research Projects

Organizational Units

Journal Issue

Access Restrictions

Abstract

Obscene and indecent content in popular music is becoming more prevalent, the historical unreliability of explicit markers has seemingly worsened with the rise of streaming as the primary method of music consumption, and the tools to remove the explicit content from song lyrics or ’clean’ a song pose a financial burden or require a degree of technical knowledge not common in the general population. This paper compares open source software for Music Source Separation, focusing on the ability to separate vocals from a musical track, and introduces an application exposing the champion through an intuitive graphic user interface. The resulting application allows users to extract vocals from an audio file, selectively remove vocals, and recombine the edited vocals with their source, effectively allowing users to create their own clean versions of their favorite music. The aim is to alleviate the financial burden associated with professional Music Source Separation software as well as increase accessibility of MSS for the layman.

Description

Keywords

Citation