The First Cadenza Challenge: Perceptual Evaluation of Machine Learning Systems to Improve Audio Quality of Popular Music for Those with Hearing Loss.
Music is central to many people's lives, and hearing loss (HL) is often a barrier to musical engagement. Hearing aids (HAs) help, but their efficacy in improving speech does not consistently translate to music. This research evaluated systems submitted to the 1st Cadenza Machine Learning Challenge,...
| Publicado en: | Trends in Hearing Vol. 30; pp. 1 - 22 |
|---|---|
| Autores principales: | , , , , , , , , , , |
| Formato: | research tables/charts Journal Article |
| Publicado: |
Sage Publications Inc.
1/30/2026
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=191254443&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 191254443 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 23312165 HCEJ jtl: Trends in Hearing issn: 23312165 maglogo: N pubinfo: dt: 1/30/2026 vid: 30 pid: 344 pub: Sage Publications Inc. place: Thousand Oaks, California artinfo: ui: 191254443 191254443 191254443 10.1177/23312165251408761 191254443 ppf: 1 ppct: 21 formats: tig: atl: The First Cadenza Challenge: Perceptual Evaluation of Machine Learning Systems to Improve Audio Quality of Popular Music for Those with Hearing Loss. aug: au: Bannister, Scott Firth, Jennifer Roa-Dabike, Gerardo Vos, Rebecca Whitmer, William Greasley, Alinka E. Graetzer, Simone Fazenda, Bruno Cox, Trevor Barker, Jon Akeroyd, Michael A. affil: School of Music, University of Leeds, Leeds, UK sug: subj: Hearing Disorders Psychosocial Factors Machine Learning Hearing Aids Evaluation Music Algorithms Quality Improvement Human Middle Age Aged Aged, 80 and Over Male Female Funding Source Perceptual Distortion Loudness Perception Signal Processing, Computer Assisted Severity of Illness Listening Audiometry Descriptive Statistics Confidence Intervals Data Analysis Software Post Hoc Analysis Spearman's Rank Correlation Coefficient Middle Aged: 45-64 years Aged: 65+ years Aged, 80 & over Male Female ab: Music is central to many people's lives, and hearing loss (HL) is often a barrier to musical engagement. Hearing aids (HAs) help, but their efficacy in improving speech does not consistently translate to music. This research evaluated systems submitted to the 1st Cadenza Machine Learning Challenge, where entrants aimed to improve music audio quality for HA users through source separation and remixing. The HA users (N = 53, ranging from "mild" to "moderately severe" HL) assessed eight challenge systems (including one baseline using the HDemucs source separation algorithm, remixing to original mixes of music samples, and applying National Acoustic Laboratories Revised amplification) and rated 200 music samples processed for their HL. Participants rated samples on basic audio quality, clarity, harshness, distortion, frequency balance, and liking. Results suggest no entrant system surpassed the baseline for audio quality, although differences emerged in system efficacy across HL severities. Clarity and distortion ratings were most predictive of audio quality. Finally, some systems produced signals with higher objective loudness, spectral flux and clipping with increasing HL severity; these received lower audio quality ratings by listeners with moderately severe HL. Findings highlight how music enhancement requires varied solutions and tests across a range of HL severities. This challenge provided a first application of source separation to music listening with HL. However, state-of-the-art source separation algorithms limited the diversity of entrant solutions, resulting in no improvements over the baseline; to promote development of innovative processing strategies, future work should increase complexity of music listening scenarios to be addressed through source separation. pubtype: Academic Journal doctype: research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|