GV-LEx, Gesture and Voice for expressive reading


GV-LEx is subsidized by the French National Agency for Research (ANR) in the scope of the 2009 project "Content and Interaction". Members of the consortium are ALDEBARAN Robotics (holder of the project), Acapela, CNRS/LIMSI and Telecom Paris Tech. Its aim is to make the robot NAO and the Avatar Greta capable of reading texts for several minutes without boring the listener with a monotoneous computer voice. To reach this objective, we propose to bring expressiveness into the speech synthesis itself as well as to take advantage of the robot or virtual human being: they are capable of performing expressive gestures while talking.

Main objectives of the project:

  • Give an artificial being the capability of expressive reading:
    • Model the expressiveness in the reading
    • Automatically recognize the expression to add in the text
    • Synthesize an expressive voice
    • Coordinate the gesture and speech expressiveness of the robot
    • Implement all the above on an avatar or humanoid robot

  • Estimate the expressiveness with children

  • Other expected results
    • Make annotated corpus available to the community
    • Create a format for emotive annotation (BML, …)

  • Project completion: December 2011.