To illustrate the potential of multilayer neural networks for adaptive interfaces, a VPL Data-Glove connected to a DECtalk speech synthesizer via five neural networks was used to implement a hand-gesture to speech system. Using minor variations of the standard backpropagation 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 word 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.
[1]
John Scott Bridle,et al.
Probabilistic Interpretation of Feedforward Classification Network Outputs, with Relationships to Statistical Pattern Recognition
,
1989,
NATO Neurocomputing.
[2]
Geoffrey E. Hinton.
20 – CONNECTIONIST LEARNING PROCEDURES1
,
1990
.
[3]
Roy K. Sedge,et al.
American Sign Language and Sign Systems
,
1980
.
[4]
Geoffrey E. Hinton,et al.
Learning representations by back-propagating errors
,
1986,
Nature.
[5]
Geoffrey E. Hinton,et al.
Building adaptive interfaces with neural networks: The glove-talk pilot study
,
1990,
INTERACT.
[6]
D. E. Rumelhart,et al.
Learning internal representations by back-propagating errors
,
1986
.