Automatic prediction of speaker age using CART
Susanne Schötz · 2005
This paper describes a small attempt to automatically estimate speaker age aimed at increasing the phonetic knowledge of age. Acoustic features were extracted from the four phonemes of the Swedish word /ra:sa / (collapse) produced by 428 adult Swedish speakers, and then used to build CARTs (Classification and Regression Trees) for prediction of age, age group and gender. Results showed that the CARTs used different strategies to estimate different phonemes, and that age predictors for /a: / and /s / performed best. The best CARTs made about 91 % correct judgements for gender, about 72 % for age group, while the correlation between biological and predicted age was about 0.45. When comparing this results to those of an earlier study of human age perception, it was found that although humans and CARTs used similar cues, the human listeners were somewhat better at estimating age. More studies with larger and more varied speech material are needed in further pursuit of a good automatic age predictor. 1