A Survey on Automated Pop Song Mashup Systems

PhD Qualifying Examination


Title: "A Survey on Automated Pop Song Mashup Systems"

by

Mr. Xinyang WU


Abstract:

Music mashups merge elements from different songs, transforming familiar 
tracks into new and captivating musical creations. Automated systems for 
generating mashups have emerged to simplify this creative process. Current 
systems commonly employ rule-based approaches for rhythmic and harmonic 
matching to ensure seamless and coherent mashup generation. Recent 
advancements have further expanded creative possibilities by integrating 
music source separation techniques and neural network-based segment 
compatibility prediction, enabling more sophisticated and musically cohesive 
mashups. However, replicating the nuance, creativity, and appeal of 
handcrafted mashups remains a significant challenge. This survey paper 
provides a comprehensive overview of the advancements in automated mashup 
generation, discussing existing techniques, their limitations, and potential 
improvements.


Date:                   Tuesday, 1 April 2025

Time:                   10:00am - 12:00noon

Venue:                  Room 3494
                        Lifts 25/26

Committee Members:      Prof. Andrew Horner (Supervisor)
                        Prof. Raymond Wong (Chairperson)
                        Dr. Arpit Narechania