Comparative Analysis of Random Forest and Support Vector Machine for Sundanese Dialect Classification Using Speech Recognition Features

This study investigates the classification of West and South Sundanese dialects using Random Forest (RF) and Support Vector Machine (SVM). Using a dataset of 100 recordings with features extracted via Mel Frequency Cepstral Coefficient (MFCC), models were evaluated by accuracy, precision, recall, and F1-score. Results show RF achieved an accuracy of 93.33%, outperforming SVM's 73.33%. The analysis demonstrates that RF is more reliable in distinguishing dialectal features. This research contributes to regional speech recognition, supporting language preservation and improved dialectal analysis.