Department of Computer Science, University of Texas at El Paso
Abstract: Today there are solutions for some specific turn-taking problems, but no general model. We show how turn-taking can be reduced to two more general problems, prediction and selection. We also discuss the value of predicting not only future speech/silence but also prosodic features, thereby handing not only turn-taking but ``turn-shaping''. To illustrate how such predictions can be made, we trained a neural network predictor. This was adequate to support some specific turn-taking decisions and was modestly accurate overall.
Full Paper (pdf)
Video of Predictions over Time (wmv, 29 seconds, 1.8Mb).
Illustrating how a predictor must make and revise predictions as the dialog proceeds.
Nigel Ward's Publications