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

Gerardo Roa Dabike, Michael A. Akeroyd, Scott Bannister, Jon Barker, Trevor J. Cox +6 more
10/5/2023
eess.AScs.LGeess.SP

Official code: claritychallenge/clarity (194 stars, MIT, last commit 2026-04-27).

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.

View on arXivView PDF

Code Implementations(1)

claritychallenge/clarityOfficial
MIT

Clarity Challenge toolkit - software for building Clarity Challenge systems

19470Shell, PythonApr 13, 20225 months agoMIT
challengeshearing-aidsmachine-learningspeech-enhancement

Similar Papers

The First Cadenza Signal Processing Challenge: Improving Music for Those With a Hearing Loss

89% match1 repo1942023

Remixing Music for Hearing Aids Using Ensemble of Fine-Tuned Source Separators

88% match2024

The first Cadenza challenges: using machine learning competitions to improve music for listeners with a hearing loss

87% match1 repo1942024

Benchmarks and leaderboards for sound demixing tasks

81% match1 repo8562023

Music Enhancement with Deep Filters: A Technical Report for The ICASSP 2024 Cadenza Challenge

80% match2024

Advances in Intelligent Hearing Aids: Deep Learning Approaches to Selective Noise Cancellation

77% match2025

Cite this paper

@article{dabike2023icassp,
  title  = {The ICASSP SP Cadenza Challenge: Music Demixing/Remixing for Hearing Aids},
  author = {Gerardo Roa Dabike and Michael A. Akeroyd and Scott Bannister and Jon Barker and Trevor J. Cox and Bruno Fazenda and Jennifer Firth and Simone Graetzer and Alinka Greasley and Rebecca R. Vos and William M. Whitmer},
  year   = {2023},
  eprint = {2310.03480},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2310.03480v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.03480.svg)](https://codeofpaper.com/paper/2310.03480)

Discussion