bluelogo.gif (1643 bytes)

home page

Glove-Talk:  A Neural Network Interface Between a Data-Glove and a Speech Synthesizer

S. Sidney Fells and Geoffrey E. Hinton
Department of Computer Science
University of Toronto


To illustrate the potential of multilayer neural networks for adaptive interfaces, we used a VPL Data-Glove connected to a DECtalk speech synthesized via five neural networks to implement a hand-gesture to speech system.  Using minor variations of the standard back-propagation learning procedure, the complex mapping of hand movements to speech is learned using data obtained from a single 'speaker' in a simple training phase.  With a 203 gesture-to-word vocabulary, the wrong is produced less than 1% of the time, and no word is produced about 5% of the time.  Adaptive control of the speaking rate and word stress is also available.  The training times and final performance speed are improved by using small, separate networks for each naturally defined subtask.  The system demonstrates that neural networks can be used to develop the complex mappings required in a high bandwidth interface that adapts to the individual user.

Download:  [ps] [pdf]

[home page]  [publications]