Abstract
This paper investigates the gender effect in speaker trait recognition especially in likability and personality detection. The acoustic features, classification methods, and feature selection techniques are adopted from the prescribed platform of the Interspeech 2012 Speaker Trait Challenge. In the proposed method, first we separate the files according to gender. Then features and classifiers are applied on gender dependent cases. In the experiments, we find that gender dependent trait recognition is higher than gender independent cases. We also find that the features and classification methods for male and female are different from the best cases. Our proposed technique outperforms the baseline result provided in the challenge in both likability and personality detection.