Instrument sound classification using a music-based feature extraction model inspired by Mozart's Turkish March pattern

In the era of advanced artificial intelligence (AI) models, the intersection of music and pattern recognition has garnered significant interest. This study investigates the application of music-inspired features for the classification of instrument sounds. A novel feature extraction model, based on the harmonic patterns observed in Mozart's Turkish March, is proposed to enhance the detection and classification of sounds. A dataset comprising over 40,000 sound samples from 28 distinct musical instruments was utilised for evaluating the proposed approach. The feature engineering (FE) model employed in this study consists of three distinct phases: feature extraction, feature selection, and classification. During the feature extraction phase, a multilevel discrete wavelet transform (MDWT) was combined with the Turkish March pattern (TurkMarchPat) to capture a comprehensive set of features. In the subsequent feature selection phase, neighbourhood component analysis (NCA) was applied to identify the most discriminative features, which were then input into a k-nearest neighbours (kNN) classifier for sound classification. The results demonstrated the effectiveness of the proposed TurkMarchPat-based FE model, achieving a classification accuracy of 97.87 % on the instrument sound dataset. These findings suggest that the application of harmonic patterns, such as those derived from Mozart’s Turkish March, offers a promising approach to sound classification, demonstrating both the robustness and efficiency of the model. The proposed method holds potential for advancing the field of acoustic pattern recognition and could be extended to other domains requiring high-performance sound classification.