Speaker Classification II - Selected Projects

Christian Müller

Lecture Notes on Artificial Intelligence (LNAI) 4441 Springer New York - Berlin 2007.


As well as conveying a message in words and sounds, the speech signal carries information about the speaker's anatomy, physiology, linguistic experience, and mental state. These characteristics are found in speech at all levels, from the spectral information in the sounds to the choice of words and utterances themselves. This two-volume set constitutes a state-of-the-art survey in the field of speaker classification. It addresses such questions as which characteristics of speakers are manifested in their voice and speaking behavior, which characteristics can be inferred from analyzing the acoustic realizations, how can this information be used, which methods are most suited to solve problems in this area of research, and how should the quality of the results be evaluated. The twenty-two articles of the second volume cover a number of areas in the field of speaker classification, including gender recognition systems, emotion recognition, text-dependent speaker verification systems, an analysis of both speaker and verbal content information, and accent identification.

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence