A Fermatean fuzzy CRITIC-MAIRCA fusion model for automated vocal performance evaluation in a.i. assisted decision support systems

Automated vocal performance assessment requires the integration of objective acoustic analysis and subjective expert opinions under uncertainty. Nevertheless, all current AI-based scoring methods ignore the issue of expert hesitation, whereas traditional Multi-Criteria Decision-Making (MCDM) models cannot simultaneously solve the problem of objective weighting and interpretable ranking. This paper will present a Fermatean Fuzzy (FF) Criteria Importance Through Intercriteria Correlation (CRITIC) Multi-Attributive Ideal-Real Comparative Analysis (MAIRCA) fusion system in automated vocal analysis decision support systems. It is a unique framework that incorporates: (i) Fermatean Fuzzy Sets (FFS) to specify expert reluctance and expression of uncertainty, (ii) the CRITIC method to obtain objective criterion weights depending on contrast intensity and inter-criteria conflict, and (iii) the MAIRCA method to produce deviation-based and interpretable rankings. The effectiveness of the proposed model is shown by a hypothetical case study that embraced six vocal performers and six multidimensional criteria. Findings indicate constant and convergent rankings, objective selection of influential criteria, and sensitivity analysis resistance. The proposed framework offers a robust, uncertainty-conscious, and bias-reduced assessment mechanism, which is more methodologically advanced than AI-only and traditional fuzzy decision- making methods in the evaluation of performance in the arts.