Natalia Marmasse and Chris Schmandt
Speech Interface Group

Communication is much more than the direct transfer of information. It is an interactive collaborative act including potentially rich verbal and non-verbal cues. Telecommunication to date has focused on verbal communication at a distance, filtering out the non-verbal situational information. With the existing infrastructure it is necessary to first contact a person before receiving feedback on what they are doing. Current communication devices do not provide a persistent sense of presence of those we connect with, nor do they create opportunities for additional communication with them.

WatchMe is a platform for mobile communication and awareness, in the form of a watch, which addresses these limitations.

WatchMe enhances communication for a subset of people with whom we want
   an open channel of rich communication and for whom we want to be available.
     These are typically people from our "inner circle" with whom we have an
       established relationship, some common grounding, and a basis of trust.

   By sharing personal context information with our "insiders"
     we can enhance the instances of non co-located communication,
       and by providing channels of non-verbal communication
         we can foster more (verbal or non-verbal) communication and
             increase the existing sense of connectedness.

     The approach is to provide insiders with updated remote awareness
       information. This mutual awareness serves two different purposes.
         First, it can strengthen the sense of presence of people we care about
           and may encourage further communication, besides being a form of
             non-verbal communication in itself.
               Second, it will provide insiders trying to contact us with enough
                  information to make an informed decision regarding our availability
                    and the most appropriate communication medium.

       This project addresses mobile communication and awareness
         of people in a closely-knit group. It aims to enhance the
           telecommunication between them by providing relevant telepresence
             and a mobile platform facilitating various channels of verbal
               and non-verbal communication.


    The main screen of the watch with icons
    representing different insiders.
       The context display. Joe left home 10 minutes ago, he is driving,
       appears to be in a conversation, and has left us 3 text and 2
       voice instant messages.

       Locations are learned from GPS data. Physical activity is classified
       from wireless accelerometers, and the presence of speech is
       determined from signal processing of the ambient audio (no speech
       recognition is performed).

dissertation document (~6 MB)

Last updated: Aug '04