Social Signal Processing Network (2009-2014)

firefox

The Social Signal Processing Network (SSPNet) is a European Network of Excellence aimed at fostering research on Social Signal Processing, the new, emerging domain aimed at providing computers with social intelligence. This is the facet of our cognitive abilities that helps us to deal with the complex web of our daily social interactions, whether these require us to be a respected leader on the workplace, a careful parent at home, or simply a person others like to have around in a moment of relaxation.

At its heart, social intelligence aims at an adaptive use, accurate interpretation and appropriate display of social signals, discrete units of behavior that can take the form of complex constellations of nonverbal behavioral cues (facial expressions, prosody, gestures, postures, etc.) that accompany any human-human (and human-machine) interaction. Several decades of research in human sciences have shown that we are surprisingly efficient at understanding social signals and the variety of attitudes conveyed by them.

This leads to the three core questions addressed by Social Signal Processing:

  1. Is it possible to detect automatically nonverbal behavioral cues in data captured with sensors like microphones and cameras?
  2. Is it possible to automatically infer attitudes from nonverbal behavioral cues detected through sensors like microphones and cameras?
  3. Is it possible to synthesize nonverbal behavioral cues conveying desired relational attitudes for embodiment of social behaviors in artificial agents, robots or other manufacts?

Most of the SSPNet works revolve around these questions and involve a tight, multidisciplinary collaboration between human sciences (psychology, anthropology, sociology, etc.) on one hand, and technology (computer vision, speech analysis and synthesis, machine learning, signal processing, etc.) on the other hand.

Contact Alessandro : August 10th, 2009.

Cross-Cultural Personality Perception (2009-2012)

Psychologists have shown that there is a correlation between nonverbal characteristics of speaking on one side, and personality traits as perceived by the listeners on the other side. For example, individuals that speak loud are perceived as more extroverted than individuals that speak soft, and individuals that speak fast are perceived as more brilliant than individuals that speak slow. The problem is that the mapping between nonverbal characteristics of speaking and perceived personality traits is, in many cases, culture dependent. In other words, the above examples are known to apply in southern Europe, but they can be wrong when applied in other cultural areas.

The goal of this project is to develop systems that address the above problem by "translating" automatically the personality of a speaker. This means that the nonverbal characteristics of a speaker, giving rise to certain personality perceptions in a given culture, should be modified automatically to give rise to the same personality perceptions in another culture. For example, the recording of a southern Mediterranean person speaking loud and fast should be modified so that the resulting voice has the nonverbal characteristics of an extrovert and brilliant person (see the above example) in the culture of a listener coming from an area different from southern Europe.

The project can be described as an application of personality psychology findings to speech analysis and synthesis. In fact, the project starts from the correlation between physical characteristics of the voice and personality traits and leads to engineering applications where 1) natural voices are analyzed to infer personality perceptions from physical characteristics, and 2) synthetic voices are modified to elicit desired personality perceptions.

Contact Alessandro : August 10th, 2009.

© 2006 A.Vinciarelli    Design by: styleshout | Valid XHTML | CSS        Home | Site Map