Singer identification model using data augmentation and enhanced feature conversion with hybrid feature vector and machine learning

EURASIP Journal on Audio, Speech, and Music Processing

Table 2 MFCC + spectral contrast classification results for New Turkish Music Dataset

Classifier	Accuracy	Precision	Recall	F-score
Extra tree	0.894	0.899	0.894	0.895
Logistic regression	0.763	0.772	0.763	0.762
Decision tree	0.525	0.532	0.525	0.523
Gaussian NB	0.561	0.624	0.561	0.560
Linear discriminant analysis	0.727	0.737	0.727	0.728
AdaBoost	0.429	0.441	0.429	0.431
GradientBoost	0.798	0.804	0.798	0.798
KNN	0.813	0.830	0.813	0.814
XGBoost	0.833	0.835	0.833	0.831
Random forest	0.818	0.827	0.818	0.818
SVM	0.768	0.769	0.768	0.767