Using automatic speech recognition and its possible effects on the voice

Abstract

Literature and individual reports contain indications that the use of speech recognition based human computer interfaces could potentially lead to vocal fatigue, or even to symptoms associated with dysphonia. While more and more people opt for a speech driven computer interface as an alternative input method to the keyboard, and these speech recognition systems become more and widely used, both in the home and office environment, it has become necessary to qualify any potential risks of voice damage. This study reports about ongoing research that investigates acoustic changes in the voice, after use of a discrete speech recognition system. Acoustic analyses were carried out on two Swedish users of such a system. So far, for one of the users, two of the acoustic parameters under investigation that could be an indicator of vocal fatigue, show a significant difference directly before and after use of a speech recognition system.