Automatic Assessment of Singer Traits in Popular Music: Gender, Age, Height and Race

We investigate fully automatic recognition of singer traits, i. e., gender, age, height and ‘race’ of the main performing artist(s) in recorded popular music. Monaural source separation techniques are combined to simultaneously enhance harmonic parts and extract the leading voice. For evaluation the UltraStar database of 581 pop music songs with 516 distinct singers is chosen. Extensive test runs with Long Short-Term Memory sequence classification reveal that binary classification of gender, height, race and age reaches up to 89.6, 72.1, 63.3 and 57.6 % unweighted accuracy on beat level in unseen test data.