Some Acoustic Cues to Human and Machine Estimation of Speaker Age

Two experiments were carried out in order to learn more about the relation between the various acoustic cues to speaker age. The first included listening tests with resynthesized stimuli, and the second comprised automatic estimation of age using the CART (Classification And Regression Trees) technique. In the first experiment, results indicate that human listeners seem to rely more on spectral cues than on F0 and duration when judging age. The results of the second experiment seem to agree with the first, as formant frequencies outperformed the other features in the CART tests. The acoustics and perception of speaker age will be studied further using a larger material and additional methods