Update: Computers, Language & Lie Detectors
In a past blog “The Language of Language” Humintell noted that computer science professor and spoken language expert Dr. Julia Hirschberg was setting out to examine what people unconsciously communicate through things such as intonation, accent and phrasing.
Now Dr. Hirschberg is teaching computers how to spot deception detection via programming them to parse speech for these such patterns mentioned above.
This lie detection software provides clues to the intentions/emotions of the voices it analysis via loudness, changes in pitch, pauses between words, ums and ahs, nervous laughs and dozens of other tiny signs that can suggest a lie.
The applications of such a device are numerous: This software could be used in call centers, business meetings and in online dating services throughout the world.
This research development is closely related to another study conducted by James Harnsberger, Ph.D. that we recently blogged about. That research also analyzed the human voice with its focus on stress indicators.
The New York Times article goes on to state that algorithms developed by Dr. Hirschberg and colleagues have been able to spot a liar 70 percent of the time in test situations.
Don’t forget Big Brother is not only watching but soon to be listening as well.