Calibration of probabilistic age recognition

• DOI: 10.21437/interspeech.2012-168
• Publication Date: 2021-08-26T09:56:12Z
• Authors: David van Leeuwen; Mohamad Hasan Bahari
• Keywords: Language in Society; BBfor2 Cohesion; PSI_SPEECH; Language & Speech Technology

The task in automatic age recognition speech technology typically is one of regression, i.e., predicting the a speaker from his/her speech. In this paper we are interested probabilistic interpretation posterior distribution predicted age. We review number measures for assessing properties distribution, and link these to detection theory, which very well understood literature. show that Gaussian distributions by least square support vector regression behave well, there only small room improvement their under assumption.