IMS GECO Database

Speech corpus of spontaneous conversations including participants' mutual social ratings and personality factors

IMS GECO database

Antje Schweitzer, Natalie Lewandowski


GECO has been created to investigate phonetic convergence in German spontaneous speech. The database consists of 46 dialogs of approx. 25 minutes length each, between previously unacquainted female subjects. 22 dialogs were in a unimodal setting, where participants could not see each other, while the remaining 24 dialogs were recorded with subjects facing each other.

The database was automatically annotated on the segment, syllable and word level using forced alignment with manually generated orthographic transcriptions.

It was designed for investigating phonetic convergence and its correlation with personality traits and scores of mutual liking and esteem, but in general the data can be used to investigate various aspects of interlocutors' behaviour in free, spontaneous dialogs, possibly considering social aspects.

The database is freely available for non-commercial research.

New in version 1.1: We included TextGrids for convenience. There were also minor changes in the annotations resulting from fixing minor errors in the transcriptions. It is now possible to obtain parameters resulting from approximating the F0 contour on each syllable using the PaIntE model. They are not included in the standard release, but we are happy to provide them on request.

If you are interested and would like to obtain the database, please send an informal email to
geco AT We will then provide details on what we need for processing your request.

The GECO database is part of the CLARIN resources catalogue (click here for the catalogue entry).


IMS GECO Database

To the top of the page