ISCA Archive Interspeech 2008
ISCA Archive Interspeech 2008

A method for automatic and dynamic estimation of discourse genre typology with prosodic features

Nicolas Obin, Anne Lacheret-Dujour, Christophe Veaux, Xavier Rodet, Anne-Catherine Simon

This paper presents a work-in-progress on the automatic analysis of discourse genre in non-elicited speech. The study is focused on the development of bottom-up methods for automatic validation of discourse typologies found in linguistic descriptions (prosodic, syntactic, pragmatic and/or contextual and situational cues). The linguistic classification examined here opposes five discourse genres +/- controlled. To test this a priori classification under prosodic criteria, we propose a method that provides an automatic and dynamic estimation of discourse genre typology i.e. of prosodic similarities between discourse genres. This is achieved in a two-step procedure: a set of discriminant prosodic patterns is estimated and then used to raise a typology of discourse genres based on prosodic similarity criterion. The discriminant analysis reveals that a small number of prosodic patterns is sufficient to discriminate the 5 discourse genres. The typological analysis reveals some multi-level caterogical oppositions on a continuous prosodic scale that can be interpreted in terms of +/- controlled speech.


doi: 10.21437/Interspeech.2008-362

Cite as: Obin, N., Lacheret-Dujour, A., Veaux, C., Rodet, X., Simon, A.-C. (2008) A method for automatic and dynamic estimation of discourse genre typology with prosodic features. Proc. Interspeech 2008, 1204-1207, doi: 10.21437/Interspeech.2008-362

@inproceedings{obin08_interspeech,
  author={Nicolas Obin and Anne Lacheret-Dujour and Christophe Veaux and Xavier Rodet and Anne-Catherine Simon},
  title={{A method for automatic and dynamic estimation of discourse genre typology with prosodic features}},
  year=2008,
  booktitle={Proc. Interspeech 2008},
  pages={1204--1207},
  doi={10.21437/Interspeech.2008-362}
}