nCommunicates with multimodal integration agent to collect user input statistics.
nStatistics based on feature structures generated by speech, gesture, and multimodal integration components.
nStatistics collected include:
qPercentage of each input type usage
qElapsed time between modalities for multimodal
input
qPercentage of correct results in interpreting each
input
qMutual disambiguation usage statistics
nGathered statistics logged in a server database, file, or passed to user via form mailer.
q
n
n