Interspeech'2005 - Eurospeech

Lisbon, Portugal
September 4-8, 2005

Distinguishing Deceptive from Non-Deceptive Speech

Julia Hirschberg (1), Stefan Benus (1), Jason M. Brenier (2), Frank Enos (1), Sarah Friedman (1), Sarah Gilman (1), Cynthia Girand (2), Martin Graciarena (3), Andreas Kathol (3), Laura Michaelis (2), Bryan L. Pellom (2), Elizabeth Shriberg (3), Andreas Stolcke (3)

(1) Columbia University, USA; (2) University of Colorado at Boulder, USA; (3) SRI International, USA

To date, studies of deceptive speech have largely been confined to descriptive studies and observations from subjects, researchers, or practitioners, with few empirical studies of the specific lexical or acoustic/prosodic features which may characterize deceptive speech. We present results from a study seeking to distinguish deceptive from non-deceptive speech using machine learning techniques on features extracted from a large corpus of deceptive and non-deceptive speech. This corpus employs an interview paradigm that includes subject reports of truth vs. lie at multiple temporal scales. We present current results comparing the performance of acoustic/prosodic, lexical, and speaker-dependent features and discuss future research directions.

Full Paper

Bibliographic reference.  Hirschberg, Julia / Benus, Stefan / Brenier, Jason M. / Enos, Frank / Friedman, Sarah / Gilman, Sarah / Girand, Cynthia / Graciarena, Martin / Kathol, Andreas / Michaelis, Laura / Pellom, Bryan L. / Shriberg, Elizabeth / Stolcke, Andreas (2005): "Distinguishing deceptive from non-deceptive speech", In INTERSPEECH-2005, 1833-1836.