Effects of Speaking Rate on Speech and Silent Speech Recognition

Abstract

Speaking rate or the speed at which a person speaks is a fundamental user characteristic. This work investigates the rate in which users speak when interacting with speech and silent speech-based methods. Results revealed that native users speak about 8% faster than non-native users, but both groups slow down at comparable rates (34-40%) when interacting with these methods, mostly to increase their accuracy rates. A follow-up experiment confirms that slowing down does improve the accuracy of these methods. Both methods yield the best accuracy rates when speaking at 0.75x of the actual speaking rate. A post-hoc error analysis revealed that speech and silent speech methods and native and non-native speakers are susceptible to different types of errors.