168535 20260213183047.0 doi 10.1016/j.jvoice.2025.11.037 sideral 147955 ART-2025-147955 eng Estevez, Mariel Universidad de Zaragoza Beyond Global Metrics: A Fairness Analysis for Interpretable Voice Disorder Detection Systems 2025 Access copy available to the general public Unrestricted We investigate and quantify demographic-dependent biases in automatic voice disorders detection (AVDD) systems by analyzing performance disparities across speaker groups, and evaluate group-specific calibration strategies for improving reliability. We conducted a comprehensive analysis of an AVDD system using existing voice disorder datasets with available demographic metadata. The study involved analyzing system performance across various demographic groups, particularly focusing on gender and age-based cohorts. Performance evaluation was based on multiple metrics, including normalized costs and cross-entropy. We employed calibration techniques trained separately on predefined demographic groups to address group-dependent miscalibration. Analysis revealed significant performance disparities across demographic groups despite strong global metrics. The system showed systematic biases, misclassifying healthy speakers over 55 as having a voice disorder and speakers with disorders aged 14–30 as healthy. Group-specific calibration improved posterior probability quality, reducing overconfidence. For young disordered speakers, low severity scores were identified as contributing to poor system performance. For older speakers, age-related voice characteristics and potential limitations in the pretrained Hubert model used as a feature extractor likely affected results. The study demonstrates that global performance metrics are insufficient for evaluating AVDD system performance. Group-specific analysis may unmask problems in system performance fairly which are hidden within global metrics. Further, group-dependent calibration strategies help mitigate biases, resulting in a more reliable indication of system confidence. These findings emphasize the need for demographic-specific evaluation and calibration in voice disorder detection systems while providing a methodological framework applicable to broader biomedical classification tasks where demographic metadata is available. info:eu-repo/grantAgreement/ES/AEI/PID2021-126061OB-C44 info:eu-repo/grantAgreement/ES/DGA/T36-23R info:eu-repo/grantAgreement/EC/H2020/101007666/EU/Exchanges for SPEech ReseArch aNd TechnOlogies/ESPERANTO This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No H2020 101007666-ESPERANTO info:eu-repo/grantAgreement/EC/H2020/101206575/EU/Mental Illness Detection and Clinical Assessment with Reliable Interpretability/MIND-CLARITY This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No H2020 101206575-MIND-CLARITY info:eu-repo/semantics/embargoedAccess All rights reserved http://www.europeana.eu/rights/rr-f/ info:eu-repo/semantics/article info:eu-repo/semantics/acceptedVersion Bonomi, Cyntia Ribas, Dayana Universidad de Zaragoza (orcid)0000-0003-3813-4998 Ortega, Alfonso Universidad de Zaragoza (orcid)0000-0002-3886-7748 Ferrer, Luciana 5008 800 Universidad de Zaragoza Dpto. Ingeniería Electrón.Com. Área Teoría Señal y Comunicac. (2025), [13 pp.] J. voice JOURNAL OF VOICE 0892-1997 5129498 http://zaguan.unizar.es/record/168535/files/texto_completo.pdf Postprint info:eu-repo/date/embargoEnd/2026-12-19 1594639 http://zaguan.unizar.es/record/168535/files/texto_completo.jpg?subformat=icon icon Postprint info:eu-repo/date/embargoEnd/2026-12-19 oai:zaguan.unizar.es:168535 articulos driver 2026-02-13-18:30:21 ARTICLE