Objectives and Results

The project aimed to develop a system capable of automatically recognizing musical instruments from audio files. Signals were transformed into spectrograms and processed using feature extraction techniques.

Several Machine Learning and Deep Learning models were implemented, including SVM, Random Forest, and Convolutional Neural Networks (CNN). The best model achieved 92% accuracy in classifying instruments such as guitar, piano, and violin.

This work strengthened skills in audio signal processing, supervised classification, and performance evaluation using metrics like accuracy and confusion matrix.