SpeechOmeter

Abstract

Individuals with neuromotor speech disorders due to con ditions such as Multiple Sclerosis, Parkinson Disease and Cerebral Palsy have soft and slurred speech. These individ uals receive speech training to increase vocal loudness and to speak slowly and clearly. Although successful in clinical settings, generalizability of these techniques to daily con versation requires technological innovation. To address this issue we designed SpeechOmeter, a Google Glass applica tion that provides unobtrusive real-time visual feedback on vocal loudness relative to the ambient noise level. The sys tem also provides clinicians with treatment adherence and performance statistics in order to further personalize speech training regimes. In a longitudinal usability study 12 in dividuals with MS increased vocal loudness when provided with feedback. A live demonstration of SpeechOmeter will enable attendees to experience the system.

Discriminating Pattern Mining for Diagnosing Reading Disorders

“…Computer science contribution for speech disorders is witnessing a great interest [10][11][12][13] and, to the best to our knowledge, this is the first work trying to help therapists which employ tachistoscopes in diagnosing by automatically collecting and analysing information.…”