Start ReadSpeaker XT


Seminar at Speech, Music and Hearing:

Detecting deception in speech: human vs. machine performance

Julia Hirschberg, TMH/KTH & Columbia University, New York


This talk will discuss production and perception studies of deceptive speech. A large corpus of deceptive and non-deceptive speech was collected to identify acoustic/prosodic and lexical cues associated with deception. I will discuss machine learning experiments to predict deception, which achieve performance which compares favorably with the performance of human judges in perception tests on the same data and task. In particular, I will describe some findings on the role of personality factors in deception detection.

(In collaboration with Frank Enos, Columbia University; Elizabeth Shriberg, Andreas Stolcke, and Martin Graciarena, SRI/ICSI; Stefan Benus, Constantine the Philosopher University)

15:15 - 17:00
Friday September 12, 2008

The seminar is held in Fantum.

| Show complete seminar list

Published by: TMH, Speech, Music and Hearing

Last updated: Wednesday, 23-Jun-2010 09:22:46 MEST