Using Fuzzy Comprehensive Evaluation Method to Evaluate the Quality of Music Performance

Music performance quality is a multifaceted concept that encompasses various aspects such as technical proficiency, emotional expression, creativity, and audience engagement. Traditional methods for evaluating musical performances frequently depend on subjective evaluations, which fail to adequately convey the complex nature of musical expression. Fuzzy comprehensive assessment offers a useful method for addressing this problem by using an organized and impartial framework for evaluating the quality of musical performance. This research proposes a novel efficient gold rush optimized fuzzy neural network (EGRO-FNN) model for evaluating the quality of music performance. The method employs fuzzy logic to quantify subjective assessments and incorporates various kinds of evaluation criteria, including technical skill, emotional expressiveness, and engagement with the audience. Data are gathered from feedback from teachers to investigate the music performance of the students. Feedback is often revealed to enhance the general quality of music performance efficiency. The data were pre-processed using min-max scaling. The features were extracted using zero crossing rate (ZCR). Through the establishment of evaluation criteria and fuzzy evaluation matrices, the approach combines subjective assessments to provide a numerical score that represents the overall performance quality analysis at three levels: good, poor, and very poor. According to the results based on Davies–Bouldin index, the parameters such as musicality (3.42), note accuracy (3.52), and rhythm accuracy (3.752) show that the suggested approach is dependable and offers accurate and impartial assessments of the quality of musical performances. These results indicate the creation of frameworks for standardized performance evaluations, which improves the efficacy of music instruction and encourages higher education music programs to raise their standards.