Abstract

In addition to technical and cost determinants, a range of human factors issues governs the appropriateness of synthesized or digitized speech for a particular system. For example, since synthesized messages are created textually, they may reflect the rules and habits of written language, rather than spoken language. This may cause listeners some difficulty interpreting the intended meaning of the message. Moreover, the different speech media place constraints upon techniques of message creation editing, transmission and reception. Synthesized speech is easy to edit in terms of lexical content, but the production of sophisticated prosodic features can be problematic. In contrast, unedited digitized speech will normally have appropriate prosodic cues and because of this will be difficult to edit. The influence of these factors is examined and illustrations of both good and poor practice are given. The paper concludes with a decision criteria checklist for speech output devices.