Classifying Speakers According to Age and Gender

Christian Müller

In: Christian Müller (Hrsg.). Speaker Classification II. Seiten 1-9 Lecture Notes in Computer Science / Artificial Intelligence (LNCS/LNAI) 4343 Springer Heidelberg - New York - Berlin 2007.


Speaker age is a speaker characteristic which is always present in speech. Previous studies have found numerous acoustic features which correlate with speaker age. However, few attempts have been made to establish their relative importance. This study automatically extracted 161 acoustic features from six words produced by 527 speakers of both genders, and used normalised means to directly compare the features. Segment duration and sound pressure level (SPL) range were identified as the most important acoustic correlates of speaker age.

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence