As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
In this article we studied the effect of using Sentence Prediction as a complementary technique to Word Prediction. A mean rate of 21.0 WPM and a maximum absolute rate of 43.4 WPM were obtained for the Sentence Prediction only condition. Combining Sentence Prediction with Word Prediction resulted in a mean rate of 18.8 WPM and a maximum absolute rate of 36.2 WPM. To measure system performance under more realistic conditions we also tested the use of Word and Sentence Prediction under different sentence knowledge conditions: 100%, 75%, 50%, 25%, 0%, and were obtained mean rates of 16.8, 14.6, 10.9, 8.6 and 8.2 WPM respectively. The conditions with less knowledge (25% and 0%) had results close to the Word Prediction only condition, around 8 WPM, which is an indicator that under low sentence re-use conditions it does not compromise user performance. Since Sentence Prediction also proved to have the potential to speed up message composition, we think this technique can be a valuable complement to Word Prediction in AAC systems.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.