Tuesday, September 25, 2012

Paper Blogs 03



Reference Paper
SHARED UNDERSTANDING AND SYNCHRONY EMERGENCE
Synchrony as an Indice of the Exchange of Meaning between Dialog Partners
Ken Prepin and Catherine Pelachaud


Overview of the Paper

In face-to-face dialog, synchrony one of the most crucial parameters claimed by the psychologist. The quality of the interaction is perceived by the human from the verbal and non-verbal synchrony. An artificial agent should be able to synchronize with its human counterpart to give the human a feeling of natural interaction. In this the authors present a dynamic model of verbal and non-verbal communication. In test simulations, they show that if the partners in dyad understand each other, then the synchrony emerges, else synchrony disrupted.

They design an interaction model between two agents, agent1 and agent2. Each agent’s state is represented by variable S. Speech produced by each agent is represented by V­act and the speech heard by each agent, the perceived signal is presented by Vper. So the dyadic communication model is represented by Figure1. Here, two ‘level of understanding’ parameters are presented by u and u’.  

                                                                    Figure1 

Again, agent’s internal states are reflected by its non-verbal behavior. The no-verbal behavior of the agent is a function of its internal state. Now after incorporating its non-verbal response, the model looks like Figure2. Here each agent shows some non-verbal act, presented by NVact. 

                                                                     Figure2
Moreover, humans are sensitive to perceived behavior and synchrony. So, a modification of this model is needed, which should include the perceived non-verbal behavior of the agent. So, after perceiving the verbal (Vper) and non-verbal (NVper) act of other agent, the agent’s internal state is changed. Figure3 presents the updated model.   

                                                                    Figure3 

These agents have internal dynamics which control their behavior and also they must be influenced by other’s behavior. The model can be expressed by the following equations.
Now, replacing the internal states S, the following equations are obtained. From these equations, it is observed that, the agents are not only influenced by the state of others, but also influenced by their own state. 



Evaluation

To simulate the result, they use neural network simulator Leto/Prometheus. This simulator updates the whole network at each time. Agent’s internal state is presented by relaxation oscillators. In each step, the neuron feeds the oscillator of both agents. The relaxation oscillator value increases linearly and decreases rapidly when it reaches the threshold value 0.95.
  
Then they simulate for 5000 time step simulates. They consider the signals synchronized if the phase shifts becomes near zero before time step 3000, are remains consistent later. A synchronization result is shown in Figure4.

                                                                     Figure4

They also try with different values of the model parameters and simulation. From their simulations, they found that, when the agents understanding do not differ more than 15%, then the agent’s will eventually be synchronized, no matter what their initial phase shift was. And, if the understanding differs more than 15%, then they will be desynchronized.

Validity of the Paper

In this paper, authors show two main results. They show that dis-synchronization happens for misunderstanding and they are very rapid. They also show that synchrony is a proof of good interaction. They use a very useful and strong analysis method, named time lag analysis.

Improvement Scopes

I think the main challenge faced by the researchers in this field is human unpredictability. It will be nice to see how this model will work on human-agent interaction in future. Moreover, the main challenges still remain to implementation this model, understanding the verbal and non-verbal behavior of human subject.

Further Reading

One of the interesting articles, which are cited by this paper, is “Nonverbal synchrony and rapport”, by Marianne LaFrance (Digital Object Identifier: 10.2307/3033875). In the cited article, the author shows that the posture sharing and rapport are positively correlated. She also presents a hypothesis that, posture sharing may be an influential factor of establishing a rapport.

References
[1] K. Prepin and C. Pelachaud, “Shared Understanding and Synchrony Emergence - Synchrony as an Indice of the Exchange of Meaning between Dialog Partners,” In proceedings of ICAART2011, International Conference on Agent and Artificial Intelligence. Rome, It. Vol. 2, pp(25- 34)

[2] M. LaFrance, “Nonverbal synchrony and rapport: Analysis by the cross-lag panel technique,” in Social Psychology Quarterly, 1979, Vol. 1,  pp(66–70)

 

No comments:

Post a Comment