The ICASSP SP Cadenza Challenge: Music Demixing/Remixing for Hearing Aids

Dabike, Gerardo Roa; Akeroyd, Michael A.; Bannister, Scott; Barker, Jon; Cox, Trevor J.; Fazenda, Bruno; Firth, Jennifer; Graetzer, Simone; Greasley, Alinka; Vos, Rebecca R.; Whitmer, William M.

Abstract

This paper reports on the design and results of the 2024 ICASSP SP Cadenza Challenge: Music Demixing/Remixing for Hearing Aids. The Cadenza project is working to enhance the audio quality of music for those with a hearing loss. The scenario for the challenge was listening to stereo reproduction over loudspeakers via hearing aids. The task was to: decompose pop/rock music into vocal, drums, bass and other (VDBO); rebalance the different tracks with specified gains and then remixing back to stereo. End-to-end approaches were also accepted. 17 systems were submitted by 11 teams. Causal systems performed poorer than non-causal approaches. 9 systems beat the baseline. A common approach was to fine-tuning pretrained demixing models. The best approach used an ensemble of models.

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)
• Start Date: Apr 14, 2024
• End Date: Apr 19, 2024
• Publication Date: Apr 14, 2024
• Deposit Date: Aug 16, 2024
• Publicly Available Date: Apr 15, 2026
• Publisher: Institute of Electrical and Electronics Engineers
• Book Title: 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)
• ISBN: 979-8-3503-7452-0
• DOI: https://doi.org/10.1109/icasspw62465.2024.10626340