A Methodology for the Evaluation of Real-Time Speech Digitization

Abstract

Real-time speech digitizing technologies underlie such modern communications products as voice store and forward systems and digital PBX's. Among the human factors design issues associated with this technology, three of particular importance can be identified: i) speaker identifiability, ii) acceptability of speech quality, and iii) speech intelligibility. An experimental method for addressing issues of identifiability and intelligibility was developed and used to compare a commercial speech digitizing device with a standard toll quality telephone channel. It was found that the identifiability and acceptability of the telephone was slightly superior to the digitized speech. Additionally, results on an MRT showed intelligibility scores somewhat below optimal.