COMPUTERIZED SPEECH RECOGNITION IN PSYCHOLOGICAL-ASSESSMENT - A MACINTOSH PROTOTYPE FOR SCREENING DEPRESSIVE SYMPTOMS

Computerized speech-recognition technology holds strong promise for ps ychological assessment. This paper focuses on a computerized speech re cognition application for screening depressive symptomatology. A Macin tosh-based prototype has been developed that uses the Center for Epide miological Studies-Depression scale (CES-D). The prototype is a HyperC ard stack interfaced with the Voice Navigator II speech recognition ap plication. The ''talking'' program represents a viable depression scre ening tool that is fully voice operated by the respondent. A pilot stu dy will assess the feasibility and acceptability of the computerized a nd written versions of the CES-D with a nonclinical adult population. A counterbalanced design will test for order effects and analyze the p sychometric equivalence of the two methods. The limitations and future directions for speech-recognition applications in psychological asses sment are discussed.