BILINGUAL COMPUTERIZED SPEECH-RECOGNITION SCREENING FOR CLINICAL DEPRESSION - EVALUATING A CELLULAR TELEPHONE PROTOTYPE

This exploratory field study evaluated a bilingual computerized speech -recognition cellular telephone prototype of the Center for Epidemiolo gical Studies-Depression scale (CES-D). Thirty Spanish and 22 English speakers completed both computer-telephone and face-to-face CES-D meth ods and an oral depression checklist in counterbalanced order. Both la nguage groups reported high positive ratings for the computer-telephon e method, with the English sample preferring the computer-telephone ov er the face-to-face method. In both samples, the computer-telephone me thod yielded high internal consistency estimates, strong alternate for m reliabilities, and similar high correlations to the depression check list. Both groups reported significantly elevated scores with the comp uter-telephone method, but total score variances for both methods did not differ. Computer-telephone limitations included occasional misreco gnitions and template training constraints.