Use of flexible voice output techniques for machine-man communication
Adrian P. Stephens, John N. Holmes · Behaviour and Information Technology · 1984
Techniques of speech synthesis potentially suitable for machine voice output were demonstrated in research laboratories 20 years ago (see, for example, Holmes et al. 1964), but have so far been restricted in application by the difficulty of generating acceptable speech with a sufficiently flexible vocabulary. JSRU's current laboratory system produces highly intelligible speech from an unlimited English vocabulary. The technique of speech synthesis by rule enables synthetic speech to be generated from conventionally spelled English text, with provision for using modified spelling or phonetic symbols for the small proportion of words that would otherwise be pronounced incorrectly. Recent advances in electronic technology have made it feasible to implement the most advanced systems for flexible speech synthesis in low-cost equipment. In addition to research towards improving the speech quality, JSRU is shortly expecting to demonstrate synthesis by rule in a self-contained voice output peripheral based on inexpensive microprocessor and signal processing integrated circuits. This paper considers some of the operational constraints which must be placed on the use of such a device if speech synthesis is to take its place as a general-purpose machine-man communication medium.