Recognition of Psychologically Relevant Aspects of Context on the Basis of Features of Speech

Anthony Jameson, Barbara Großmann-Hutter, Christian Müller, Frank Wittig, Jürgen Kiefer, Ralf Rummer

In: Proceedings of the Second International Workshop on Modeling and Retrieval of Context. International Workshop on Modeling and Retrieval of Context (MRC-2005) located at in conjunction with IJCAI'05 July 31-August 1 Edinburgh United Kingdom 2005.


Especiallyinmobilesystems,oneimportantpartofthecontextofuse involves psychological variables like cognitive load and time pressure. This ab- stract looks at one possible way of capturing such aspects of context: the analysis of features of the users’ speech. In a replication and extension of an earlier study of our group, we created four experimental conditions that varied in terms of whether the user was (a) navigating within a simulated airport terminal or stand- ing still; and (b) subject to time pressure or not. The speech produced by these subjects was coded in terms of 7 variables. We trained dynamic Bayesian net- works on the resulting data in order to see how well the information in the users’ speech could serve as evidence as to which condition the user had been in. The results give information about the accuracy that can be attained in this way, the methods that can be used to implement the classifiers, and the diagnostic value of some specific features of speech.

jamesonEtAl2005.pdf (pdf, 190 KB )

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz